Professional-Machine-Learning-Engineer Google Professional Machine Learning Engineer Questions and Answers

The best option for developing and comparing multiple models on a large-scale BigQuery table using TensorFlow and Vertex AI is to use TensorFlow I/O’s BigQuery Reader to directly read the data. This option has the following advantages:

It minimizes any bottlenecks during the data ingestion stage, as the BigQuery Reader can stream data from BigQuery to TensorFlow in parallel and in batches, without loading the entire table into memory or disk. The BigQuery Reader can also perform data transformations and filtering using SQL queries, reducing the need for additional preprocessing steps in TensorFlow.

It leverages the scalability and performance of BigQuery, as the BigQuery Reader can handle hundreds of millions of records worth of training data efficiently and reliably. BigQuery is a serverless, fully managed, and highly scalable data warehouse that can run complex queries over petabytes of data in seconds.

It simplifies the integration with Vertex AI, as the BigQuery Reader can be used with both custom and pre-built TensorFlow models on Vertex AI. Vertex AI is a unified platform for machine learning that provides various tools and features for data ingestion, data labeling, data preprocessing, model training, model tuning, model deployment, model monitoring, and model explainability.

The other options are less optimal for the following reasons:

Option A: Using the BigQuery client library to load data into a dataframe, and using tf.data.Dataset.from_tensor_slices() to read it, introduces memory and performance issues. This option requires loading the entire BigQuery table into a Pandas dataframe, which can consume a lot of memory and cause out-of-memory errors. Moreover, using tf.data.Dataset.from_tensor_slices() to read the dataframe can be slow and inefficient, as it creates one slice per row of the dataframe, resulting in a large number of small tensors.

Option B: Exporting data to CSV files in Cloud Storage, and using tf.data.TextLineDataset() to read them, introduces additional steps and complexity. This option requires exporting the BigQuery table to one or more CSV files in Cloud Storage, which can take a long time and consume a lot of storage space. Moreover, using tf.data.TextLineDataset() to read the CSV files can be slow and error-prone, as it requires parsing and decoding each line of text, handling missing values and invalid data, and applying data transformations and validations.

Option C: Converting the data into TFRecords, and using tf.data.TFRecordDataset() to read them, introduces additional steps and complexity. This option requires converting the BigQuery table into one or more TFRecord files, which are binary files that store serialized TensorFlow examples. This can take a long time and consume a lot of storage space. Moreover, using tf.data.TFRecordDataset() to read the TFRecord files requires defining and parsing the schema of the TensorFlow examples, which can be tedious and error-prone.

References:

[TensorFlow I/O documentation]

[BigQuery documentation]

[Vertex AI documentation]

According to the official exam guide1, one of the skills assessed in the exam is to “design, build, and productionalize ML models to solve business challenges using Google Cloud technologies”. Document AI2 is a document understanding platform that takes unstructured data from documents and transforms it into structured data, making it easier to understand, analyze, and consume. Document AI Workbench3 allows you to create custom extractors to parse the text in specific sections of your documents. Natural Language API4 is a service that provides natural language understanding technologies, such as sentiment analysis, entity analysis, and other text annotations. The analyzeSentiment feature5 inspects the given text and identifies the prevailing emotional opinion within the text, especially to determine a writer’s attitude as positive, negative, or neutral. Therefore, option C is the best way to accomplish the task of predicting an overall satisfaction score from the customer comments on each form. The other options are not relevant or optimal for this scenario. References:

Professional ML Engineer Exam Guide

Document AI

Document AI Workbench

Natural Language API

Sentiment analysis

Google Professional Machine Learning Certification Exam 2023

Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

The best option for productionizing a Keras model is to use TensorFlow Extended (TFX), a framework for building end-to-end machine learning pipelines that can handle large-scale data and complex workflows. TFX provides standard components for data ingestion, transformation, validation, analysis, training, tuning, serving, and monitoring. TFX pipelines can be orchestrated with Vertex AI Pipelines, a managed service that runs on Google Cloud Platform and leverages Kubernetes and Argo. Vertex AI Pipelines allows you to automate the execution of your TFX pipeline steps, schedule retraining jobs, and scale up or down the resources as needed. By using TFX and Vertex AI Pipelines, you can take advantage of the following benefits:

You can reuse the existing code in your Jupyter notebook, as TFX supports Keras as a first-class citizen. You can also use the Keras Tuner to optimize your model hyperparameters.

You can ensure data quality and consistency by using the TFX Data Validation component, which can detect anomalies, drift, and skew in your data. You can also use the TFX SchemaGen component to generate a schema for your data and enforce it throughout the pipeline.

You can analyze your model performance and fairness by using the TFX Model Analysis component, which can produce various metrics and visualizations. You can also use the TFX Model Validation component to compare your new model with a baseline model and set thresholds for deploying the model to production.

You can deploy your model to various serving platforms by using the TFX Pusher component, which can push your model to Vertex AI, Cloud AI Platform, TensorFlow Serving, or TensorFlow Lite. You can also use the TFX Model Registry to manage the versions and metadata of your models.

You can monitor your model performance and health by using the TFX Model Monitor component, which can detect data drift, concept drift, and prediction skew in your model. You can also use the TFX Evaluator component to compute metrics and validate your model against a baseline or a slice of data.

You can reduce the cost and complexity of managing your own infrastructure by using Vertex AI Pipelines, which provides a serverless environment for running your TFX pipeline. You can also use the Vertex AI Experiments and Vertex AI TensorBoard to track and visualize your pipeline runs.

References:

[TensorFlow Extended (TFX)]

[Vertex AI Pipelines]

[TFX User Guide]

According to the official exam guide1, one of the skills assessed in the exam is to “design, build, and productionalize ML models to solve business challenges using Google Cloud technologies”. AutoML Vision2 is a service that allows you to train and deploy custom vision models for image classification and object detection. AutoML Vision simplifies the model development process by providing a graphical user interface and a no-code approach. You can use AutoML Vision to train an object detection model by using the annotated image data, and evaluate the model performance using metrics such as mean average precision (mAP) and intersection over union (IoU)3. Therefore, option B is the best way to quickly create an initial model for the given use case. The other options are not relevant or optimal for this scenario. References:

Professional ML Engineer Exam Guide

AutoML Vision

Object detection evaluation

Google Professional Machine Learning Certification Exam 2023

Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

 The trace in the question shows that the training time is taking longer than expected. This is likely due to the input function not being optimized. To decrease training time in a cost-efficient way, the best option is to rewrite the input function using parallel reads, parallel processing, and prefetch. This will allow the model to process the data more efficiently and decrease training time. References:

[Cloud TPU Performance Guide]

[Data input pipeline performance guide]

A ResourceExhaustedError: out of memory (OOM) when allocating tensor is an error that occurs when the GPU runs out of memory while trying to allocate memory for a tensor. A tensor is a multi-dimensional array of numbers that represents the data or the parameters of a machine learning model. The size and shape of a tensor depend on various factors, such as the input data, the model architecture, the batch size, and the optimization algorithm1.

For the use case of training a computer vision model that predicts the type of government ID present in a given image using a GPU-powered virtual machine on Compute Engine, the best option to resolve the error is to reduce the batch size. The batch size is a parameter that determines how many input examples are processed at a time by the model. A larger batch size can improve the model’s accuracy and stability, but it also requires more memory and computation. A smaller batch size can reduce the memory and computation requirements, but it may also affect the model’s performance and convergence2.

By reducing the batch size, the GPU can allocate less memory for each tensor, and avoid running out of memory. Reducing the batch size can also speed up the training process, as the GPU can process more batches in parallel. However, reducing the batch size too much may also have some drawbacks, such as increasing the noise and variance of the gradient updates, and slowing down the convergence of the model. Therefore, the optimal batch size should be chosen based on the trade-off between memory, computation, and performance3.

The other options are not as effective as option B, because they are not directly related to the memory allocation of the GPU. Option A, changing the optimizer, may affect the speed and quality of the optimization process, but it may not reduce the memory usage of the model. Option C, changing the learning rate, may affect the convergence and stability of the model, but it may not reduce the memory usage of the model. Option D, reducing the image shape, may reduce the size of the input tensor, but it may also reduce the quality and resolution of the image, and affect the model’s accuracy. Therefore, option B, reducing the batch size, is the best answer for this question.

References:

ResourceExhaustedError: OOM when allocating tensor with shape - Stack Overflow

How does batch size affect model performance and training time? - Stack Overflow

How to choose an optimal batch size for training a neural network? - Stack Overflow

According to the official exam guide1, one of the skills assessed in the exam is to “track the lineage of pipeline artifacts”. Vertex AI Experiments2 is a service that allows you to track and compare the results of your model training runs. Vertex AI Experiments automatically logs metadata such as hyperparameters, metrics, and artifacts for each training run. You can use Vertex AI Experiments to train your custom model using TensorFlow, PyTorch, XGBoost, or scikit-learn. Vertex AI Model Registry3 is a service that allows you to manage your trained models in a central location. You can use Vertex AI Model Registry to register your model, add labels and descriptions, and view the model’s lineage graph. The lineage graph shows the artifacts and executions that are part of the model’s creation, such as the dataset, the training pipeline, and the evaluation metrics. The other options are not relevant or optimal for this scenario. References:

Professional ML Engineer Exam Guide

Vertex AI Experiments

Vertex AI Model Registry

Google Professional Machine Learning Certification Exam 2023

Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

The easiest way to integrate custom Python code into the Kubeflow Pipelines SDK is to use the func_to_container_op function, which converts a Python function into a pipeline component. This function automatically builds a Docker image that executes the Python function, and returns a factory function that can be used to create kfp.dsl.ContainerOp instances for the pipeline. This option has the following benefits:

It allows the data science team to reuse their existing Python code without rewriting it or packaging it into containers manually.

It simplifies the component specification and implementation, as the function signature defines the component interface and the function body defines the component logic.

It supports various types of inputs and outputs, such as primitive types, files, directories, and dictionaries.

The other options are less optimal for the following reasons:

Option B: Using the predefined components available in the Kubeflow Pipelines SDK to access Dataproc, and run the custom code there, introduces additional complexity and cost. This option requires creating and managing Dataproc clusters, which are ephemeral and scalable clusters of Compute Engine instances that run Apache Spark and Apache Hadoop. Moreover, this option requires writing the custom code in PySpark or Hadoop MapReduce, which may not be compatible with the existing Python code.

Option C: Packaging the custom Python code into Docker containers, and using the load_component_from_file function to import the containers into the pipeline, introduces additional steps and overhead. This option requires creating and maintaining Dockerfiles, building and pushing Docker images, and writing component specifications in YAML files. Moreover, this option requires managing the dependencies and versions of the Python code and the Docker images.

Option D: Deploying the custom Python code to Cloud Functions, and using Kubeflow Pipelines to trigger the Cloud Function, introduces additional latency and limitations. This option requires creating and deploying Cloud Functions, which are serverless functions that execute in response to events. Moreover, this option requires invoking the Cloud Functions from the Kubeflow Pipelines using HTTP requests, which can incur network overhead and latency. Additionally, this option is subject to the quotas and limits of Cloud Functions, such as the maximum execution time and memory usage.

References:

Building Python function-based components | Kubeflow

Building Python Function-based Components | Kubeflow

 The best option for creating and orchestrating an end-to-end training pipeline for a TensorFlow model is to use TensorFlow Extended (TFX) and standard TFX components, and deploy the pipeline to Vertex AI Pipelines. TFX is an end-to-end platform for deploying production ML pipelines, which consists of several built-in components that cover the entire ML lifecycle, from data ingestion and validation, to model training and evaluation, to model deployment and monitoring. TFX also supports custom components and integrations with other Google Cloud services, such as BigQuery, Dataflow, and Cloud Storage. Vertex AI Pipelines is a fully managed service that allows you to run TFX pipelines on Google Cloud, without having to worry about infrastructure provisioning, scaling, or maintenance. Vertex AI Pipelines also provides a user-friendly interface to monitor and manage your pipelines, as well as tools to track and compare experiments. The other options are not as suitable for creating and orchestrating an end-to-end training pipeline for a TensorFlow model, because:

Creating the pipeline using Kubeflow Pipelines domain-specific language (DSL) and predefined Google Cloud components would require more development time and effort, as Kubeflow Pipelines DSL is not as expressive or compatible with TensorFlow as TFX. Predefined Google Cloud components might not cover all the stages of the ML lifecycle, and might not be optimized for TensorFlow models.

Orchestrating the pipeline using Kubeflow Pipelines deployed on Google Kubernetes Engine would require more infrastructure maintenance, as Kubeflow Pipelines is not a fully managed service, and you would have to provision and manage your own Kubernetes cluster. This would also incur more costs, as you would have to pay for the cluster resources, regardless of the pipeline usage. References:

TFX | ML Production Pipelines | TensorFlow

Vertex AI Pipelines | Google Cloud

Kubeflow Pipelines | Google Cloud

Google Cloud launches machine learning engineer certification

Google Professional Machine Learning Engineer Certification

Professional ML Engineer Exam Guide

The best option for scaling a Vertex AI endpoint efficiently when the demand increases in the future, using a scikit-learn model that is deployed to a Vertex AI endpoint and tested on live production traffic, is to configure an appropriate minReplicaCount value based on expected baseline traffic. This option allows you to leverage the power and simplicity of Vertex AI to automatically scale your endpoint resources according to the traffic patterns. Vertex AI is a unified platform for building and deploying machine learning solutions on Google Cloud. Vertex AI can deploy a trained model to an online prediction endpoint, which can provide low-latency predictions for individual instances. Vertex AI can also provide various tools and services for data analysis, model development, model deployment, model monitoring, and model governance. A minReplicaCount value is a parameter that specifies the minimum number of replicas that the endpoint must always have, regardless of the load. A minReplicaCount value can help you ensure that the endpoint has enough resources to handle the expected baseline traffic, and avoid high latency or errors. By configuring an appropriate minReplicaCount value based on expected baseline traffic, you can scale your endpoint efficiently when the demand increases in the future. You can set the minReplicaCount value when you deploy the model to the endpoint, or update it later. Vertex AI will automatically scale up or down the number of replicas within the range of the minReplicaCount and maxReplicaCount values, based on the target utilization percentage and the autoscaling metric1.

The other options are not as good as option B, for the following reasons:

Option A: Deploying two models to the same endpoint and distributing requests among them evenly would not allow you to scale your endpoint efficiently when the demand increases in the future, and could increase the complexity and cost of the deployment process. A model is a resource that represents a machine learning model that you can use for prediction. A model can have one or more versions, which are different implementations of the same model. A model version can help you experiment and iterate on your model, and improve the model performance and accuracy. An endpoint is a resource that provides the service endpoint (URL) you use to request the prediction. An endpoint can have one or more deployed models, which are instances of model versions that are associated with physical resources. A deployed model can help you serve online predictions with low latency, and scale up or down based on the traffic. By deploying two models to the same endpoint and distributing requests among them evenly, you can create a load balancing mechanism that can distribute the traffic across the models, and reduce the load on each model. However, deploying two models to the same endpoint and distributing requests among them evenly would not allow you to scale your endpoint efficiently when the demand increases in the future, and could increase the complexity and cost of the deployment process. You would need to write code, create and configure the two models, deploy the models to the same endpoint, and distribute the requests among them evenly. Moreover, this option would not use the autoscaling feature of Vertex AI, which can automatically adjust the number of replicas based on the traffic patterns, and provide various benefits, such as optimal resource utilization, cost savings, and performance improvement2.

Option C: Setting the target utilization percentage in the autoscalingMetricSpecs configuration to a higher value would not allow you to scale your endpoint efficiently when the demand increases in the future, and could cause errors or poor performance. A target utilization percentage is a parameter that specifies the desired utilization level of each replica. A target utilization percentage can affect the speed and accuracy of the autoscaling process. A higher target utilization percentage can help you reduce the number of replicas, but it can also cause high latency, low throughput, or resource exhaustion. By setting the target utilization percentage in the autoscalingMetricSpecs configuration to a higher value, you can increase the utilization level of each replica, and save some resources. However, setting the target utilization percentage in the autoscalingMetricSpecs configuration to a higher value would not allow you to scale your endpoint efficiently when the demand increases in the future, and could cause errors or poor performance. You would need to write code, create and configure the autoscalingMetricSpecs, and set the target utilization percentage to a higher value. Moreover, this option would not ensure that the endpoint has enough resources to handle the expected baseline traffic, which could cause high latency or errors1.

Option D: Changing the model’s machine type to one that utilizes GPUs would not allow you to scale your endpoint efficiently when the demand increases in the future, and could increase the complexity and cost of the deployment process. A machine type is a parameter that specifies the type of virtual machine that the prediction service uses for the deployed model. A machine type can affect the speed and accuracy of the prediction process. A machine type that utilizes GPUs can help you accelerate the computation and processing of the prediction, and handle more prediction requests at the same time. By changing the model’s machine type to one that utilizes GPUs, you can improve the prediction performance and efficiency of your model. However, changing the model’s machine type to one that utilizes GPUs would not allow you to scale your endpoint efficiently when the demand increases in the future, and could increase the complexity and cost of the deployment process. You would need to write code, create and configure the model, deploy the model to the endpoint, and change the machine type to one that utilizes GPUs. Moreover, this option would not use the autoscaling feature of Vertex AI, which can automatically adjust the number of replicas based on the traffic patterns, and provide various benefits, such as optimal resource utilization, cost savings, and performance improvement2.

References:

Configure compute resources for prediction | Vertex AI | Google Cloud

Deploy a model to an endpoint | Vertex AI | Google Cloud

Option A is incorrect because using Kubeflow Pipelines on Google Kubernetes Engine is not the most convenient way to orchestrate the entire pipeline with minimal cluster management. Kubeflow Pipelines is an open-source platform that allows you to build, run, and manage ML pipelines using containers1. Google Kubernetes Engine is a service that allows you to create and manage clusters of virtual machines that run Kubernetes, an open-source system for orchestrating containerized applications2. However, this option requires more effort and resources than option B, as it involves creating and configuring the clusters, installing and maintaining Kubeflow Pipelines, and writing and running the pipeline code.

Option B is correct because using Vertex AI Pipelines with TensorFlow Extended (TFX) SDK is the best way to orchestrate the entire pipeline with minimal cluster management. Vertex AI Pipelines is a service that allows you to create and run scalable and portable ML pipelines on Google Cloud3. TensorFlow Extended (TFX) is a framework that provides a set of components and libraries for building production-ready ML pipelines using TensorFlow4. You can use Vertex AI Pipelines with TFX SDK to ingest and preprocess the data in Cloud Storage, train and tune the object model using Vertex AI jobs, and deploy the model to an endpoint, using predefined or custom components. Vertex AI Pipelines handles the underlying infrastructure and orchestration for you, so you don’t need to worry about cluster management or scalability.

Option C is incorrect because using Vertex AI Pipelines with Kubeflow Pipelines SDK is not the most suitable way to orchestrate the entire pipeline with minimal cluster management. Kubeflow Pipelines SDK is a library that allows you to build and run ML pipelines using Kubeflow Pipelines5. You can use Vertex AI Pipelines with Kubeflow Pipelines SDK to create and run ML pipelines on Google Cloud, using containers. However, this option is less convenient and consistent than option B, as it requires you to use different APIs and tools for different steps of the pipeline, such as Vertex AI SDK for training and deployment, and Kubeflow Pipelines SDK for ingestion and preprocessing. Moreover, this option does not leverage the benefits of TFX, such as the standard components, the metadata store, or the ML Metadata library.

Option D is incorrect because using Cloud Composer for the orchestration is not the most efficient way to orchestrate the entire pipeline with minimal cluster management. Cloud Composer is a service that allows you to create and run workflows using Apache Airflow, an open-source platform for orchestrating complex tasks. You can use Cloud Composer to orchestrate the entire pipeline, by creating and managing DAGs (directed acyclic graphs) that define the dependencies and order of the tasks. However, this option is more complex and costly than option B, as it involves creating and configuring the environments, installing and maintaining Airflow, and writing and running the DAGs.

References:

Kubeflow Pipelines documentation

Google Kubernetes Engine documentation

Vertex AI Pipelines documentation

TensorFlow Extended documentation

Kubeflow Pipelines SDK documentation

[Cloud Composer documentation]

[Vertex AI documentation]

[Cloud Storage documentation]

[TensorFlow documentation]

 Parallel interleave is a technique that can improve the performance of the input pipeline by reading and processing data from multiple files in parallel. This can reduce the idle time of the GPU and speed up the training process. Parallel interleave can be implemented using the tf.data.experimental.parallel_interleave () function in TensorFlow, which takes a map function that returns a dataset for each input element, and a cycle length that determines how many input elements are processed concurrently. Parallel interleave can also handle different file sizes and processing times by using a block length argument that controls how many consecutive elements are produced from each input element before switching to another input element. For more information about parallel interleave and how to use it, see the following references:

How to use parallel_interleave in TensorFlow

Better performance with the tf.data API

 Recommendations AI is a service that allows users to build, test, and deploy personalized product recommendations for their ecommerce websites. It uses Google’s deep learning models to learn from user behavior and product data, and generate high-quality recommendations that can increase revenue, click-through rate, and customer satisfaction. One of the best practices for using Recommendations AI is to choose the right recommendation type for the business objective. The “Frequently Bought Together” recommendation type shows products that are often purchased together with the current product, and encourages users to add more items to their shopping cart. This can increase the average order value and the revenue for each transaction. The other options are not as effective or feasible for this objective. The “Other Products You May Like” recommendation type shows products that are similar to the current product, and may increase the click-through rate, but not necessarily the shopping cart size. Importing the user events and then the product catalog is not a recommended order, as it may cause data inconsistency and missing recommendations. The product catalog should be imported first, and then the user events. Using placeholder values for the product catalog is not a viable option, as it will not produce meaningful recommendations or reflect the real performance of the model. References:

Recommendations AI documentation

Choosing a recommendation type

Importing data to Recommendations AI

According to the official exam guide1, one of the skills assessed in the exam is to “configure and optimize model monitoring jobs”. The Vertex AI Model Monitoring documentation states that “to reduce the cost of model monitoring, you can configure the sample rate of the requests that are logged and analyzed by model monitoring”. Therefore, decreasing the sample_rate parameter in the Randomsampleconfig of the monitoring job would reduce the model monitoring cost while continuing to quickly detect drift. The other options are not relevant or optimal for this scenario. References:

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Professional ML Engineer Exam Guide

Google Professional Machine Learning Certification Exam 2023

Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

[Vertex AI Model Monitoring]

 The best option for splitting the data between the training, validation, and test sets, using a managed tabular dataset in Vertex AI that contains sales data from three different stores, is to use Vertex AI default data split. This option allows you to leverage the power and simplicity of Vertex AI to automatically and randomly split your data into the three sets by percentage. Vertex AI is a unified platform for building and deploying machine learning solutions on Google Cloud. Vertex AI can support various types of models, such as linear regression, logistic regression, k-means clustering, matrix factorization, and deep neural networks. Vertex AI can also provide various tools and services for data analysis, model development, model deployment, model monitoring, and model governance. A default data split is a data split method that is provided by Vertex AI, and does not require any user input or configuration. A default data split can help you split your data into the training, validation, and test sets by using a random sampling method, and assign a fixed percentage of the data to each set. A default data split can help you simplify the data split process, and works well in most cases. A training set is a subset of the data that is used to train the model, and adjust the model parameters. A training set can help you learn the relationship between the input features and the target variable, and optimize the model performance. A validation set is a subset of the data that is used to validate the model, and tune the model hyperparameters. A validation set can help you evaluate the model performance on unseen data, and avoid overfitting or underfitting. A test set is a subset of the data that is used to test the model, and provide the final evaluation metrics. A test set can help you assess the model performance on new data, and measure the generalization ability of the model. By using Vertex AI default data split, you can split your data into the training, validation, and test sets by using a random sampling method, and assign the following percentages of the data to each set1:

The other options are not as good as option B, for the following reasons:

Option A: Using Vertex AI manual split, using the store name feature to assign one store for each set would not allow you to split your data into representative and balanced sets, and could cause errors or poor performance. A manual split is a data split method that allows you to control how your data is split into sets, by using the ml_use label or the data filter expression. A manual split can help you customize the data split logic, and handle complex or non-standard data formats. A store name feature is a feature that indicates the name of the store where the sales data was collected. A store name feature can help you identify the source of the data, and group the data by store. However, using Vertex AI manual split, using the store name feature to assign one store for each set would not allow you to split your data into representative and balanced sets, and could cause errors or poor performance. You would need to write code, create and configure the ml_use label or the data filter expression, and assign one store for each set. Moreover, this option would not ensure that the data in each set has the same distribution and characteristics as the data in the whole dataset, which could prevent you from learning the general pattern of the data, and cause bias or variance in the model2.

Option C: Using Vertex AI chronological split and specifying the sales timestamp feature as the time variable would not allow you to split your data into representative and balanced sets, and could cause errors or poor performance. A chronological split is a data split method that allows you to split your data into sets based on the order of the data. A chronological split can help you preserve the temporal dependency and sequence of the data, and avoid data leakage. A sales timestamp feature is a feature that indicates the date and time when the sales data was collected. A sales timestamp feature can help you track the changes and trends of the data over time, and capture the seasonality and cyclicality of the data. However, using Vertex AI chronological split and specifying the sales timestamp feature as the time variable would not allow you to split your data into representative and balanced sets, and could cause errors or poor performance. You would need to write code, create and configure the time variable, and split the data by the order of the time variable. Moreover, this option would not ensure that the data in each set has the same distribution and characteristics as the data in the whole dataset, which could prevent you from learning the general pattern of the data, and cause bias or variance in the model3.

Option D: Using Vertex AI random split, assigning 70% of the rows to the training set, 10% to the validation set, and 20% to the test set would not allow you to use the default data split method that is provided by Vertex AI, and could increase the complexity and cost of the data split process. A random split is a data split method that allows you to split your data into sets by using a random sampling method, and assign a custom percentage of the data to each set. A random split can help you split your data into representative and balanced sets, and avoid data leakage. However, using Vertex AI random split, assigning 70% of the rows to the training set, 10% to the validation set, and 20% to the test set would not allow you to use the default data split method that is provided by Vertex AI, and could increase the complexity and cost of the data split process. You would need to write code, create and configure the random split method, and assign the custom percentages to each set. Moreover, this option would not use the default data split method that is provided by Vertex AI, which can simplify the data split process, and works well in most cases1.

References:

About data splits for AutoML models | Vertex AI | Google Cloud

Manual split for unstructured data

Mathematical split

Option A is incorrect because migrating your model to TensorFlow, and training it using Vertex AI Training, is not the easiest way to improve the model’s training time. TensorFlow is a framework that allows you to create and train ML models using Python or other languages. Vertex AI Training is a service that allows you to train and optimize ML models using built-in algorithms or custom containers. However, this option requires significant code changes, as TensorFlow and scikit-learn have different APIs and functionalities. Moreover, this option does not leverage the parallelism or the scalability of the cloud, as it only uses a single instance.

Option B is incorrect because training your model in a distributed mode using multiple Compute Engine VMs, is not the most convenient way to improve the model’s training time. Compute Engine is a service that allows you to create and manage virtual machines that run on Google Cloud. You can use Compute Engine to run your scikit-learn model in a distributed mode, by using libraries such as Dask or Joblib. However, this option requires more effort and resources than option D, as it involves creating and configuring the VMs, installing and maintaining the libraries, and writing and running the distributed code.

Option C is incorrect because training your model with DLVM images on Vertex AI, and ensuring that your code utilizes NumPy and SciPy internal methods whenever possible, is not the most effective way to improve the model’s training time. DLVM (Deep Learning Virtual Machine) images are preconfigured VM images that include popular ML frameworks and tools, such as TensorFlow, PyTorch, or scikit-learn1. You can use DLVM images on Vertex AI to train your scikit-learn model, by using a custom container. NumPy and SciPy are libraries that provide numerical and scientific computing functionalities for Python. You can use NumPy and SciPy internal methods to optimize your scikit-learn code, as they are faster and more efficient than pure Python code2. However, this option does not leverage the parallelism or the scalability of the cloud, as it only uses a single instance. Moreover, this option may not have a significant impact on the training time, as scikit-learn already relies on NumPy and SciPy for most of its operations3.

Option D is correct because training your model using Vertex AI Training with GPUs, is the best way to improve the model’s training time. A GPU (Graphics Processing Unit) is a hardware accelerator that can perform parallel computations faster than a CPU (Central Processing Unit)4. Vertex AI Training is a service that allows you to train and optimize ML models using built-in algorithms or custom containers. You can use Vertex AI Training with GPUs to train your scikit-learn model, by using a custom container and specifying the accelerator type and count5. By using Vertex AI Training with GPUs, you can leverage the parallelism and the scalability of the cloud, and speed up the training process significantly, without changing your code.

References:

DLVM images

NumPy and SciPy

scikit-learn dependencies

GPU overview

Vertex AI Training with GPUs

[scikit-learn overview]

[TensorFlow overview]

[Compute Engine overview]

[Dask overview]

[Joblib overview]

[Vertex AI Training overview]

The simplest way to deploy a logistic regression model with BigQuery ML to production while adding minimal latency is to export the model in TensorFlow format, and add a tfx_bsl.public.beam.RunInference step to the Dataflow pipeline. This option has the following advantages:

It allows the model prediction to be performed in real time, as part of the Dataflow streaming pipeline that processes the ticket purchase requests. This ensures that the promo code offer is based on the most recent data and customer behavior, and that the offer is delivered to the customer without delay.

It leverages the compatibility and performance of TensorFlow and Dataflow, which are both part of the Google Cloud ecosystem. TensorFlow is a popular and powerful framework for building and deploying machine learning models, and Dataflow is a fully managed service that runs Apache Beam pipelines for data processing and transformation. By using the tfx_bsl.public.beam.RunInference step, you can easily integrate your TensorFlow model with your Dataflow pipeline, and take advantage of the parallelism and scalability of Dataflow.

It simplifies the model deployment and management, as the model is packaged with the Dataflow pipeline and does not require a separate service or endpoint. The model can be updated by redeploying the Dataflow pipeline with a new model version.

The other options are less optimal for the following reasons:

Option A: Running batch inference with BigQuery ML every five minutes on each new set of tickets issued introduces additional latency and complexity. This option requires running a separate BigQuery job every five minutes, which can incur network overhead and latency. Moreover, this option requires storing and retrieving the intermediate results of the batch inference, which can consume storage space and increase the data transfer time.

Option C: Exporting the model in TensorFlow format, deploying it on Vertex AI, and querying the prediction endpoint from the streaming pipeline introduces additional latency and cost. This option requires creating and managing a Vertex AI endpoint, which is a managed service that provides various tools and features for machine learning, such as training, tuning, serving, and monitoring. However, querying the Vertex AI endpoint from the streaming pipeline requires making an HTTP request, which can incur network overhead and latency. Moreover, this option requires paying for the Vertex AI endpoint usage, which can increase the cost of the model deployment.

Option D: Converting the model with TensorFlow Lite (TFLite), and adding it to the mobile app so that the promo code and the incoming request arrive together in Pub/Sub introduces additional challenges and risks. This option requires converting the model to a TFLite format, which is a lightweight and optimized format for running TensorFlow models on mobile and embedded devices. However, converting the model to TFLite may not preserve the accuracy or functionality of the original model, as some operations or features may not be supported by TFLite. Moreover, this option requires updating the mobile app with the TFLite model, which can be tedious and time-consuming, and may depend on the user’s willingness to update the app. Additionally, this option may expose the model to potential security or privacy issues, as the model is running on the user’s device and may be accessed or modified by malicious actors.

References:

[Exporting models for prediction | BigQuery ML]

[tfx_bsl.public.beam.run_inference | TensorFlow Extended]

[Vertex AI documentation]

[TensorFlow Lite documentation]

Vertex AI is a unified platform for building and managing machine learning solutions on Google Cloud. It provides a managed service for training custom models with various frameworks, such as TensorFlow, PyTorch, scikit-learn, and XGBoost. To train your PyTorch model with Vertex AI, you need to package your code with Setuptools, which is a Python tool for creating and distributing packages. You also need to use a pre-built container, which is a Docker image that contains the dependencies and libraries for your framework. You can choose from a list of pre-built containers provided by Google, or create your own custom container. By using a pre-built container, you can avoid the hassle of installing and configuring the environment for your model. You can also specify a custom tier for your training job, which allows you to select the number and type of GPUs you want to use. You can choose from various GPU options, such as V100, P100, K80, and T4. By using 4 V100 GPUs, you can leverage the high performance and memory capacity of these accelerators to train your model faster and cheaper than using CPUs. This solution requires minimal changes to your code and can scale your training workload efficiently. References:

Vertex AI | Google Cloud

Custom training with pre-built containers | Vertex AI

[Using GPUs | Vertex AI]

The best hardware to choose for your model while minimizing cost is a Vertex AI Workbench user-managed notebooks instance running on an n1-standard-16 with a preemptible v3-8 TPU. This hardware configuration can provide you with high performance, scalability, and efficiency for your TensorFlow model, as well as low cost and flexibility for your long-running and checkpointing process. The v3-8 TPU is a cloud tensor processing unit (TPU) device, which is a custom ASIC chip designed by Google to accelerate ML workloads. It can handle large and complex models and datasets, and offer fast and stable training and inference. The n1-standard-16 is a general-purpose VM that can support the CPU and memory requirements of your model, as well as the data preprocessing and postprocessing tasks. By choosing a preemptible v3-8 TPU, you can take advantage of the lower price and availability of the TPU devices, as long as you can tolerate the possibility of the device being reclaimed by Google at any time. However, since you have built frequent checkpointing into your training process, you can resume your model from the last saved state, and avoid losing any progress or data. Moreover, you can use the Vertex AI Workbench user-managed notebooks to create and manage your notebooks instances, and leverage the integration with Vertex AI and other Google Cloud services.

The other options are not optimal for the following reasons:

A. A Vertex AI Workbench user-managed notebooks instance running on an n1-standard-16 with 4 NVIDIA P100 GPUs is not a good option, as it has higher cost and lower performance than the v3-8 TPU. The NVIDIA P100 GPUs are the previous generation of GPUs from NVIDIA, which have lower performance, scalability, and efficiency than the latest NVIDIA A100 GPUs or the TPUs. They also have higher price and lower availability than the preemptible TPUs, which can increase the cost and complexity of your solution.

B. A Vertex AI Workbench user-managed notebooks instance running on an n1-standard-16 with an NVIDIA P100 GPU is not a good option, as it has higher cost and lower performance than the v3-8 TPU. It also has less GPU memory and compute power than the option with 4 NVIDIA P100 GPUs, which can limit the size and complexity of your model, and affect the training and inference speed and quality.

C. A Vertex AI Workbench user-managed notebooks instance running on an n1-standard-16 with a non-preemptible v3-8 TPU is not a good option, as it has higher cost and lower flexibility than the preemptible v3-8 TPU. The non-preemptible v3-8 TPU has the same performance, scalability, and efficiency as the preemptible v3-8 TPU, but it has higher price and lower availability, as it is reserved for your exclusive use. Moreover, since your model is long-running and checkpointing, you do not need the guarantee of the device not being reclaimed by Google, and you can benefit from the lower cost and higher availability of the preemptible v3-8 TPU.

References:

Professional ML Engineer Exam Guide

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Google Cloud launches machine learning engineer certification

Cloud TPU

Vertex AI Workbench user-managed notebooks

Preemptible VMs

NVIDIA Tesla P100 GPU

Cloud Vision API offers pre-trained models specialized in identifying explicit or inappropriate content. By sending a copy of each image to a Cloud Storage bucket and triggering Cloud Vision through Cloud Run, the detection of explicit content is automated with minimal development time. Vertex AI custom models require more training data and infrastructure management, while AutoML-based solutions add more complexity. Cloud Vision’s existing capabilities meet the requirement effectively and are highly scalable for real-time moderation needs.

=================

Option A is incorrect because using latitude, longitude, and product type as features, and using profit as model output is not the best way to develop an ML model to predict the company’s profitability for a new line of naturally flavored bottled waters in different locations. This option does not capture the interaction between latitude and longitude, which may affect the profitability of the product. For example, the same product may have different profitability in different regions, depending on the climate, culture, or preferences of the customers. Moreover, this option does not account for the granularity of the location data, which may be too fine or too coarse for the model. For example, using the exact coordinates of a city may not be meaningful, as the profitability may vary within the city, or using the country name may not be informative, as the profitability may vary across the country.

Option B is incorrect because using latitude, longitude, and product type as features, and using revenue and expenses as model outputs is not a suitable way to develop an ML model to predict the company’s profitability for a new line of naturally flavored bottled waters in different locations. This option has the same drawbacks as option A, as it does not capture the interaction between latitude and longitude, or account for the granularity of the location data. Moreover, this option does not directly predict the profitability of the product, which is the target variable of interest. Instead, it predicts the revenue and expenses of the product, which are intermediate variables that depend on other factors, such as the price, the cost, or the demand of the product. To obtain the profitability, we would need to subtract the expenses from the revenue, which may introduce errors or uncertainties in the prediction.

Option C is correct because using product type and the feature cross of latitude with longitude, followed by binning, as features, and using profit as model output is a good way to develop an ML model to predict the company’s profitability for a new line of naturally flavored bottled waters in different locations. This option captures the interaction between latitude and longitude, which may affect the profitability of the product, by creating a feature cross of these two features. A feature cross is a synthetic feature that combines the values of two or more features into a single feature1. This option also accounts for the granularity of the location data, by binning the feature cross into discrete buckets. Binning is a technique that groups continuous values into intervals, which can reduce the noise and complexity of the data2. Moreover, this option directly predicts the profitability of the product, which is the target variable of interest, by using it as the model output.

Option D is incorrect because using product type and the feature cross of latitude with longitude, followed by binning, as features, and using revenue and expenses as model outputs is not a valid way to develop an ML model to predict the company’s profitability for a new line of naturally flavored bottled waters in different locations. This option has the same advantages as option C, as it captures the interaction between latitude and longitude, and accounts for the granularity of the location data, by creating a feature cross and binning it. However, this option does not directly predict the profitability of the product, which is the target variable of interest, but rather predicts the revenue and expenses of the product, which are intermediate variables that depend on other factors, as explained in option B.

References:

Feature cross

Binning

[Profitability]

[Revenue and expenses]

[Latitude and longitude]

[Product type]

A random forest is an ensemble learning method that consists of many decision trees. It can be used for both regression and classification tasks. A random forest classification model can predict the probability of churn for each customer by assigning them to different classes, such as high-risk, medium-risk, or low-risk. A random forest model can also generate feature importances, which measure how much each feature contributes to the prediction. Feature importances can help interpret the model and understand what factors influence customer churn. Vertex AI Workbench is an integrated development environment (IDE) that allows you to create and run Jupyter notebooks on Google Cloud. You can use Vertex AI Workbench to build a random forest classification model in Python, using libraries such as scikit-learn or TensorFlow. You can also configure the model to generate feature importances after the model is trained, and visualize them using plots or tables. This solution can help you build an interpretable model for customer churn prediction, and use the results to design marketing campaigns that target at-risk customers. References:

Random Forests | scikit-learn

Vertex AI Workbench | Google Cloud

Interpreting Random Forests | Towards Data Science

 Sentiment analysis is the process of identifying and extracting the emotions, opinions, and attitudes expressed in a text or speech. Sentiment analysis can help businesses understand their customers’ feedback, satisfaction, and preferences. There are different approaches to building a sentiment analysis tool, depending on the input data and the output format. Some of the common approaches are:

Extracting sentiment directly from the voice recordings: This approach involves using acoustic features, such as pitch, intensity, and prosody, to infer the sentiment of the speaker. This approach can capture the nuances and subtleties of the vocal expression, but it also requires a large and diverse dataset of labeled voice recordings, which may not be easily available or accessible. Moreover, this approach may not account for the semantic and contextual information of the speech, which can also affect the sentiment.

Converting the speech to text and building a model based on the words: This approach involves using automatic speech recognition (ASR) to transcribe the voice recordings into text, and then using lexical features, such as word frequency, polarity, and valence, to infer the sentiment of the text. This approach can leverage the existing text-based sentiment analysis models and tools, but it also introduces some challenges, such as the accuracy and reliability of the ASR system, the ambiguity and variability of the natural language, and the loss of the acoustic information of the speech.

Converting the speech to text and extracting sentiments based on the sentences: This approach involves using ASR to transcribe the voice recordings into text, and then using syntactic and semantic features, such as sentence structure, word order, and meaning, to infer the sentiment of the text. This approach can capture the higher-level and complex aspects of the natural language, such as negation, sarcasm, and irony, which can affect the sentiment. However, this approach also requires more sophisticated and advanced natural language processing techniques, such as parsing, dependency analysis, and semantic role labeling, which may not be readily available or easy to implement.

Converting the speech to text and extracting sentiment using syntactical analysis: This approach involves using ASR to transcribe the voice recordings into text, and then using syntactical analysis, such as part-of-speech tagging, phrase chunking, and constituency parsing, to infer the sentiment of the text. This approach can identify the grammatical and structural elements of the natural language, such as nouns, verbs, adjectives, and clauses, which can indicate the sentiment. However, this approach may not account for the pragmatic and contextual information of the speech, such as the speaker’s intention, tone, and situation, which can also influence the sentiment.

For the use case of building a sentiment analysis tool that predicts customer sentiment from recorded phone conversations, the best approach is to convert the speech to text and extract sentiments based on the sentences. This approach can balance the trade-offs between the accuracy, complexity, and feasibility of the sentiment analysis tool, while ensuring that the gender, age, and cultural differences of the customers who called the contact center do not impact any stage of the model development pipeline and results. This approach can also handle different types and levels of sentiment, such as polarity (positive, negative, or neutral), intensity (strong or weak), and emotion (anger, joy, sadness, etc.). Therefore, converting the speech to text and extracting sentiments based on the sentences is the best approach for this use case.

According to the web search results, Reduction Server is a faster GPU all-reduce algorithm developed at Google that uses a dedicated set of reducers to aggregate gradients from workers12. Reducers are lightweight CPU VM instances that are significantly cheaper than GPU VMs2. Therefore, the third worker pool should not have any accelerators, and should use a machine type that has high network bandwidth to optimize the communication between workers and reducers2. TPUs are not supported by Reduction Server, so the first two worker pools should have GPUs and use a container image that contains the training code12. The reduction-server container image is provided by Google and should be used for the third worker pool2.

Dynamic range quantization is a model optimization technique for reducing latency that reduces the numerical precision of the weights and activations of models. This technique can reduce the model size, memory usage, and inference time by up to 4x with negligible accuracy loss. Dynamic range quantization can be applied to a trained TensorFlow model without retraining, and it is suitable for mobile applications that require low latency and power consumption.

Weight pruning, model distillation, and dimensionality reduction are also model optimization techniques for reducing latency, but they have some limitations or drawbacks compared to dynamic range quantization:

Weight pruning works by removing parameters within a model that have only a minor impact on its predictions. Pruned models are the same size on disk, and have the same runtime latency, but can be compressed more effectively. This makes pruning a useful technique for reducing model download size, but not for reducing inference time.

Model distillation works by training a smaller and simpler model (student) to mimic the behavior of a larger and complex model (teacher). Distilled models can have lower latency and memory usage than the original models, but they require retraining and may not preserve the accuracy of the teacher model.

Dimensionality reduction works by reducing the number of features or dimensions in the input data or the model layers. Dimensionality reduction can improve the computational efficiency and generalization ability of models, but it may also lose some information or introduce noise in the data or the model. Dimensionality reduction also requires retraining or modifying the model architecture.

References:

[TensorFlow Model Optimization]

[TensorFlow Model Optimization Toolkit — Post-Training Integer Quantization]

[Model optimization methods to cut latency, adapt to new data]

According to the official exam guide1, one of the skills assessed in the exam is to “design, build, and productionalize ML models to solve business challenges using Google Cloud technologies”. The Speech-to-Text API2 allows you to convert audio to text by applying powerful neural network models. The Natural Language API3 enables you to analyze text and extract information about the sentiment, entities, and syntax. The Cloud Functions4 service lets you write and deploy code that runs in response to events, such as a Pub/Sub message or an HTTP request. Therefore, option B is the most efficient approach to analyze the audio files for customer sentiment, as it leverages the existing Google Cloud services and avoids unnecessary data processing and model training. The other options are not relevant or optimal for this scenario. References:

Professional ML Engineer Exam Guide

Speech-to-Text API

Natural Language API

Cloud Functions

Google Professional Machine Learning Certification Exam 2023

Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

Vertex AI Pipelines is a service that allows you to orchestrate and automate your machine learning (ML) workflows using pipelines1. A pipeline is a description of an ML workflow, including all of the components in the workflow, how the components are connected as a graph, and the runtime parameters that the pipeline accepts1. Vertex AI Pipelines helps you manage the end-to-end lifecycle of your ML projects, from data preprocessing to model deployment1.

Vertex AI Feature Store is a service that enables you to serve, share, and reuse ML features across different models and projects2. A feature is a measurable property or characteristic of an entity, such as the age of a person or the price of a product2. Vertex AI Feature Store helps you reduce data duplication, ensure data consistency, and improve model performance2.

Vertex AI Experiments is a service that helps you track and compare the performance of different versions of your models3. You can use Vertex AI Experiments to run multiple training jobs with different hyperparameters, architectures, or data sources, and then compare the results using metrics, visualizations, and reports3. Vertex AI Experiments helps you identify the best model for your use case and optimize your model performance3. References:

Vertex AI Pipelines | Google Cloud

Vertex AI Feature Store | Google Cloud

Vertex AI Experiments | Google Cloud

 Deploying a model to an endpoint in Vertex AI associates physical resources with the model so it can serve online predictions with low latency1. By configuring the model deployment settings to use an n1-standard-4 machine type and setting the minReplicaCount value to 1 and the maxReplicaCount value to 8, you can ensure that the model scales according to the traffic, thereby minimizing latency and cost1. The n1-standard-4 machine type provides a balance between computing power and cost, and the dynamic scaling allows the model to handle higher traffic during nights and weekends without incurring unnecessary costs during off-peak times

Vertex Explainable AI is a set of tools and frameworks to help you understand and interpret predictions made by your machine learning models, natively integrated with a number of Google’s products and services1. With Vertex Explainable AI, you can generate feature-based explanations that show how much each input feature contributed to the model’s prediction2. This can help you debug and improve your model performance, and build confidence in your model’s behavior. Feature-based explanations are supported for custom image classification models deployed on Vertex AI Prediction3. References:

Explainable AI | Google Cloud

Introduction to Vertex Explainable AI | Vertex AI | Google Cloud

Supported model types for feature-based explanations | Vertex AI | Google Cloud

TFX ModelValidator is a tool that allows you to compare new models against a baseline model and evaluate their performance on different metrics and data slices1. You can use this tool to validate your models before deploying them to production and ensure that they meet your expectations and requirements.

k-fold cross-validation is a technique that splits the data into k subsets and trains the model on k-1 subsets while testing it on the remaining subset. This is repeated k times and the average performance is reported2. This technique is useful for estimating the generalization error of a model, but it does not account for the dynamic nature of customer behavior or the potential changes in data distribution over time.

Using the last relevant week of data as a validation set is a simple way to check the model’s performance on recent data, but it may not be representative of the entire data or capture the long-term trends and patterns. It also does not allow you to compare the model with a baseline or evaluate it on different data slices.

Using the entire dataset and treating the AUC ROC as the main metric is not a good practice because it does not leave any data for validation or testing. It also assumes that the AUC ROC is the only metric that matters, which may not be true for your business problem. You may want to consider other metrics such as precision, recall, or revenue.

Data Catalog is a fully managed and scalable metadata management service that allows you to quickly discover, manage, and understand your data in Google Cloud. You can use Data Catalog to search the BigQuery datasets by using keywords in the table description, as well as other metadata attributes such as table name, column name, labels, tags, and more. Data Catalog also provides a rich browsing experience that lets you explore the schema, preview the data, and access the BigQuery console directly from the Data Catalog UI. Data Catalog helps you find the data that you need for your model building on AI Platform without writing any code or queries.

References:

[Data Catalog documentation]

[Data Catalog overview]

[Searching for data assets]

TFRecord is a binary file format that stores your data as a sequence of binary strings1. TFRecord files are efficient, scalable, and easy to process1. Sharding is a technique that splits a large file into smaller files, which can improve parallelism and performance2. Dataflow is a service that allows you to create and run data processing pipelines on Google Cloud3. Dataflow can create sharded TFRecord files from your images in a Cloud Storage directory4.

tf.data.TFRecordDataset is a class that allows you to read and parse TFRecord files in TensorFlow. You can use this class to create a tf.data.Dataset object that represents your input data for training. tf.data.Dataset is a high-level API that provides various methods to transform, batch, shuffle, and prefetch your data.

Vertex AI Training is a service that allows you to train your custom models on Google Cloud using various hardware accelerators, such as GPUs. Vertex AI Training supports TensorFlow models and can read data from Cloud Storage. You can use Vertex AI Training to train your image classification model by using a V100 GPU, which is a powerful and fast GPU for deep learning.

References:

TFRecord and tf.Example | TensorFlow Core

Sharding | TensorFlow Core

Dataflow | Google Cloud

Creating sharded TFRecord files | Google Cloud

[tf.data.TFRecordDataset | TensorFlow Core v2.6.0]

[tf.data: Build TensorFlow input pipelines | TensorFlow Core]

[Vertex AI Training | Google Cloud]

[NVIDIA Tesla V100 GPU | NVIDIA]

Kubeflow Pipelines allows for efficient use of compute resources through parallel task execution and caching, which eliminates redundant executions1. By enabling caching in all the steps of the Kubeflow pipeline, you can avoid re-running the same steps when you execute the pipeline multiple times. This can significantly speed up the pipeline execution and reduce your development time without incurring additional costs

Precision and recall are two common metrics for evaluating the performance of a classification model. Precision measures the proportion of positive predictions that are correct, while recall measures the proportion of positive examples that are correctly predicted. Precision and recall are inversely related, meaning that increasing one will decrease the other, and vice versa. The trade-off between precision and recall depends on the goal and the cost of the classification problem1.

For the use case of detecting whether posted images contain cars, precision is more important than recall, as the social media company wants to minimize the number of false positives, or images that are incorrectly labeled as containing cars. A high precision means that the model is confident and accurate in its positive predictions, while a low recall means that the model may miss some positive examples, or images that actually contain cars. The cost of missing some positive examples is lower than the cost of making wrong positive predictions, as the latter may affect the user experience and the reputation of the social media company.

The softmax function is a function that transforms a vector of real numbers into a probability distribution over the possible classes. The softmax function is often used as the final layer of a neural network for multi-class classification problems, as it assigns a probability to each class, and the class with the highest probability is chosen as the prediction. The softmax function is defined as:

softmax (x_i) = exp (x_i) / sum_j exp (x_j)

where x_i is the input value for class i, and softmax (x_i) is the output probability for class i.

The softmax threshold is a parameter that determines the minimum probability that a class must have to be chosen as the prediction. For example, if the softmax threshold is 0.5, then the class with the highest probability must have at least 0.5 to be selected, otherwise the prediction is none. The softmax threshold can be used to adjust the trade-off between precision and recall, as a higher threshold will increase the precision and decrease the recall, while a lower threshold will decrease the precision and increase the recall2.

For the use case of detecting whether posted images contain cars, the best way to adjust the model’s final layer softmax threshold to increase precision is to decrease the recall. This means that the softmax threshold should be increased, so that the model will only make positive predictions when it is highly confident, and avoid making false positives. By increasing the softmax threshold, the model will become more selective and accurate in its positive predictions, and improve the precision metric. Therefore, decreasing the recall is the best option for this use case.

References:

Precision and recall - Wikipedia

How to add a threshold in softmax scores - Stack Overflow

Option A is not the best answer because it requires storing the pickled model in Cloud Storage, which may incur additional cost and latency for loading the model. It also requires building a Flask-based app, which may not be necessary for a simple data preprocessing step.

Option B is not the best answer because it requires building a Flask-based app, which may not be necessary for a simple data preprocessing step. It also requires packaging the app and the pickled model in a custom container image, which may increase the size and complexity of the image.

Option C is not the best answer because it requires packaging the pickled model in a custom container image, which may increase the size and complexity of the image. It also does not leverage the Vertex built-in container image, which may provide some optimizations and integrations for XGBoost models.

Option D is the best answer because it leverages the Vertex built-in container image, which may provide some optimizations and integrations for XGBoost models. It also allows storing the pickled model in Cloud Storage, which may reduce the size and complexity of the image. It also allows building a custom predictor class based on XGBoost Predictor from the Vertex AI SDK, which may simplify the data preprocessing step and the prediction logic.

Cloud Data Fusion is a fully managed, cloud-native data integration service that helps users efficiently build and manage ETL/ELT data pipelines. It provides a graphical interface to increase time efficiency and reduce complexity, and allows users to easily create and explore data pipelines using a code-free, point and click visual interface. Cloud Data Fusion also supports a broad range of data sources and formats, including on-premises data marts, and ensures data quality and security by using built-in transformation capabilities and Cloud Data Loss Prevention. Cloud Data Fusion lowers the total cost of ownership by handling performance, scalability, availability, security, and compliance needs automatically. References:

Cloud Data Fusion documentation

Cloud Data Fusion overview

A fairness metric is a way to measure how well a machine learning model treats different groups of customers, such as by sex or age. A common fairness metric is accuracy, which is the proportion of correct predictions among all predictions. Accuracy across the sensitive features means calculating the accuracy for each group separately, and then comparing them. For example, if the model has 90% accuracy for male customers and 80% accuracy for female customers, there is a 10% accuracy gap that indicates potential bias against female customers.

To investigate and mitigate potential bias, it is important to define a fairness metric and evaluate it on a test set. A test set is a subset of the data that is not used for training the model, but only for evaluating its performance. By joining the test set predictions with the sensitive features, you can calculate the fairness metric and see if it meets your requirements. For example, you may require that the accuracy gap between any two groups is less than 5%. If the fairness metric does not meet your requirements, you may need to adjust the model or the data to reduce bias.

Option A is not the best answer because excluding the sensitive features and any meaningfully correlated features may not eliminate bias. For example, if salary is correlated with sex, and salary is also a predictive feature for the target variable, excluding both features may reduce the model accuracy and still leave some residual bias. Moreover, excluding features based on correlation may not capture the complex interactions and dependencies among the features that may affect bias.

Option B is not the best answer because using the global attribution values for each feature of the model may not reflect the individual-level impact of the features on the predictions. Global attribution values are calculated by averaging the attribution values across all the data points, and they indicate how important each feature is for the overall model performance. However, they do not show how each feature affects each customer’s prediction, which may vary depending on the values of the other features. For example, sex may have a low global attribution value, but it may have a high impact on some customers’ predictions, especially if it interacts with other features such as salary or age.

Option C is not the best answer because discarding the model and training the model again without a feature based on a single customer’s attribution value may not be a robust or scalable way to mitigate bias. Attribution values are calculated by measuring how much each feature contributes to the prediction for a given data point, and they indicate how sensitive the prediction is to the feature value. However, they do not show how the feature affects the overall fairness metric or the model accuracy. For example, sex may have a high attribution value for a customer, but it may not affect the accuracy gap between the groups. Moreover, discarding and retraining the model based on a single customer’s attribution value may not be feasible if there are many customers with high attribution values for different features.

Vertex AI is a unified platform for building and deploying ML models on Google Cloud. It supports both custom and AutoML models, and provides various tools and services for ML development, such as Vertex Pipelines, Vertex Vizier, Vertex Explainable AI, and Vertex Feature Store. Vertex AI can be used to create models for predicting ticket priority and resolution time, as these are domain-specific tasks that require custom training data and evaluation metrics. Cloud Natural Language API is a pre-trained service that provides natural language understanding capabilities, such as sentiment analysis, entity analysis, syntax analysis, and content classification. Cloud Natural Language API can be used to perform sentiment analysis on the support tickets, as this is a general task that does not require domain-specific knowledge or jargon. The other options are not suitable for the given architecture. AutoML Natural Language and AutoML Vision are services that allow users to create custom natural language and vision models using their own data and labels. They are not needed for sentiment analysis, as Cloud Natural Language API already provides this functionality. Cloud Vision API is a pre-trained service that provides image analysis capabilities, such as object detection, face detection, text detection, and image labeling. It is not relevant for the support tickets, as they are not expected to have any images. References:

Vertex AI documentation

Cloud Natural Language API documentation

Option A is not the best answer because it requires modifying the pipeline to use the Vertex AI Feature Store, which may not be feasible or necessary for recovering the data that the model was trained on. The Vertex AI Feature Store is a service that helps you manage, store, and serve feature values for your machine learning models1, but it is not designed for storing the raw data or the TFRecord files.

Option B is the best answer because it leverages the lineage feature of Vertex AI Metadata, which is a service that helps you track and manage the metadata of your machine learning workflows, such as datasets, models, metrics, and parameters2. The lineage feature allows you to view the relationships and dependencies among the artifacts and executions in your pipeline, and trace back the origin and history of any artifact3. By using the lineage feature, you can find the model artifact, determine the version of the model, identify the step that creates the data copy, and search in the metadata for its location.

Option C is not the best answer because it relies on the logging features in the Vertex AI endpoint, which may not be accurate or reliable for finding the data copy. The logging features in the Vertex AI endpoint help you monitor and troubleshoot the online predictions made by your deployed models, but they do not provide information about the training data or the pipeline steps4. Moreover, the timestamp of the model deployment may not match the timestamp of the pipeline run, as there may be delays or errors in the deployment process.

Option D is not the best answer because it requires finding the job ID in Vertex AI Training, which may not be easy or straightforward. Vertex AI Training is a service that helps you train your custom models on Google Cloud, but it does not provide a direct way to link the training job to the model version or the pipeline run. Moreover, searching in the logs of the job may not reveal the location of the data copy, as the logs may only contain information about the training process and the metrics.

References:

1: Introduction to Vertex AI Feature Store | Vertex AI | Google Cloud

2: Introduction to Vertex AI Metadata | Vertex AI | Google Cloud

3: View lineage for ML workflows | Vertex AI | Google Cloud

4: Monitor online predictions | Vertex AI | Google Cloud

[5]: Train custom models | Vertex AI | Google Cloud

Option A is correct because using local feature importance from the predictions is the best way to provide the reasons that contributed to the model’s decision for a specific customer’s loan request. Local feature importance is a measure of how much each feature affects the prediction for a given instance, relative to the average prediction for the dataset1. AutoML Tables provides local feature importance values for each prediction, which can be accessed using the Vertex AI SDK for Python or the Cloud Console2. By using local feature importance, you can explain why the model rejected the loan request based on the customer’s data.

Option B is incorrect because using the correlation with target values in the data summary page is not a good way to provide the reasons that contributed to the model’s decision for a specific customer’s loan request. The correlation with target values is a measure of how much each feature is linearly related to the target variable for the entire dataset, not for a single instance3. The data summary page in AutoML Tables shows the correlation with target values for each feature, as well as other statistics such as mean, standard deviation, and histogram4. However, these statistics are not useful for explaining the model’s decision for a specific customer, as they do not account for the interactions between features or the non-linearity of the model.

Option C is incorrect because using the feature importance percentages in the model evaluation page is not a good way to provide the reasons that contributed to the model’s decision for a specific customer’s loan request. The feature importance percentages are a measure of how much each feature affects the overall accuracy of the model for the entire dataset, not for a single instance5. The model evaluation page in AutoML Tables shows the feature importance percentages for each feature, as well as other metrics such as precision, recall, and confusion matrix. However, these metrics are not useful for explaining the model’s decision for a specific customer, as they do not reflect the individual contribution of each feature for a given prediction.

Option D is incorrect because varying features independently to identify the threshold per feature that changes the classification is not a feasible way to provide the reasons that contributed to the model’s decision for a specific customer’s loan request. This method involves changing the value of one feature at a time, while keeping the other features constant, and observing how the prediction changes. However, this method is not practical, as it requires making multiple prediction requests, and may not capture the interactions between features or the non-linearity of the model.

References:

Local feature importance

Getting local feature importance values

Correlation with target values

Data summary page

Feature importance percentages

[Model evaluation page]

[Varying features independently]

Vertex AI Feature Store is a service that allows you to store and manage your ML features on Google Cloud. You can use Vertex AI Feature Store to store features such as parcels delivered and truck locations over time, and retrieve them with low latency for online prediction. Online prediction is a type of prediction that provides low-latency responses to individual or small batches of input data. You can also use Vertex AI Feature Store to retrieve historical data at a specific point in time for model training. Model training is a process of learning the parameters of a ML model from data. By using Vertex AI Feature Store, you can store the features with minimal effort, and avoid the complexity of managing your own data storage and serving system. References:

Vertex AI Feature Store documentation

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

The best option for resolving the training-serving skew alert is to update the model monitoring job to use the more recent training data that was used to retrain the model. This option can help align the baseline distribution of the model monitoring job with the current distribution of the production data, and eliminate the false positive alerts. Model Monitoring is a service that can track and compare the results of multiple machine learning runs. Model Monitoring can monitor the model’s prediction input data for feature skew and drift. Training-serving skew occurs when the feature data distribution in production deviates from the feature data distribution used to train the model. If the original training data is available, you can enable skew detection to monitor your models for training-serving skew. Model Monitoring uses TensorFlow Data Validation (TFDV) to calculate the distributions and distance scores for each feature, and compares them with a baseline distribution. The baseline distribution is the statistical distribution of the feature’s values in the training data. If the distance score for a feature exceeds an alerting threshold that you set, Model Monitoring sends you an email alert. However, if you retrain the model with more recent training data, and deploy it back to the Vertex AI endpoint, the baseline distribution of the model monitoring job may become outdated and inconsistent with the current distribution of the production data. This can cause the model monitoring job to generate false positive alerts, even if the model performance is not deteriorated. To avoid this problem, you need to update the model monitoring job to use the more recent training data that was used to retrain the model. This can help the model monitoring job to recalculate the baseline distribution and the distance scores, and compare them with the current distribution of the production data. This can also help the model monitoring job to detect any true positive alerts, such as a sudden change in the production data that causes the model performance to degrade1.

The other options are not as good as option B, for the following reasons:

Option A: Updating the model monitoring job to use a lower sampling rate would not resolve the training-serving skew alert, and could reduce the accuracy and reliability of the model monitoring job. The sampling rate is a parameter that determines the percentage of prediction requests that are logged and analyzed by the model monitoring job. Using a lower sampling rate can reduce the storage and computation costs of the model monitoring job, but also the quality and validity of the data. Using a lower sampling rate can introduce sampling bias and noise into the data, and make the model monitoring job miss some important features or patterns of the data. Moreover, using a lower sampling rate would not address the root cause of the training-serving skew alert, which is the mismatch between the baseline distribution and the current distribution of the production data2.

Option C: Temporarily disabling the alert, and enabling the alert again after a sufficient amount of new production traffic has passed through the Vertex AI endpoint, would not resolve the training-serving skew alert, and could expose the model to potential risks and errors. Disabling the alert would stop the model monitoring job from sending email notifications when the distance score for a feature exceeds the alerting threshold, but it would not stop the model monitoring job from calculating and comparing the distributions and distance scores. Therefore, disabling the alert would not address the root cause of the training-serving skew alert, which is the mismatch between the baseline distribution and the current distribution of the production data. Moreover, disabling the alert would prevent the model monitoring job from detecting any true positive alerts, such as a sudden change in the production data that causes the model performance to degrade. This can expose the model to potential risks and errors, and affect the user satisfaction and trust1.

Option D: Temporarily disabling the alert until the model can be retrained again on newer training data, and retraining the model again after a sufficient amount of new production traffic has passed through the Vertex AI endpoint, would not resolve the training-serving skew alert, and could cause unnecessary costs and efforts. Disabling the alert would stop the model monitoring job from sending email notifications when the distance score for a feature exceeds the alerting threshold, but it would not stop the model monitoring job from calculating and comparing the distributions and distance scores. Therefore, disabling the alert would not address the root cause of the training-serving skew alert, which is the mismatch between the baseline distribution and the current distribution of the production data. Moreover, disabling the alert would prevent the model monitoring job from detecting any true positive alerts, such as a sudden change in the production data that causes the model performance to degrade. This can expose the model to potential risks and errors, and affect the user satisfaction and trust. Retraining the model again on newer training data would create a new model version, but it would not update the model monitoring job to use the newer training data as the baseline distribution. Therefore, retraining the model again on newer training data would not resolve the training-serving skew alert, and could cause unnecessary costs and efforts1.

References:

Preparing for Google Cloud Certification: Machine Learning Engineer, Course 3: Production ML Systems, Week 4: Evaluation

Google Cloud Professional Machine Learning Engineer Exam Guide, Section 3: Scaling ML models in production, 3.3 Monitoring ML models in production

Official Google Cloud Certified Professional Machine Learning Engineer Study Guide, Chapter 6: Production ML Systems, Section 6.3: Monitoring ML Models

Using Model Monitoring

Understanding the score threshold slider

Sampling rate

The F1 score is a metric that combines both precision and recall, and is suitable for evaluating imbalanced classification problems. Precision measures the fraction of true positives among the predicted positives, and recall measures the fraction of true positives among the actual positives. The F1 score is the harmonic mean of precision and recall, and it ranges from 0 to 1, with higher values indicating better performance. The F1 score is a good metric for imbalanced data because it balances both the false positives and the false negatives, and does not favor the majority class over the minority class.

The other options are not good metrics for imbalanced data. RMSE (root mean squared error) is a metric for regression problems, not classification problems. It measures the average squared difference between the predicted and the actual values, and is not suitable for binary outcomes. F score with higher precision weighting than recall, or F0.5 score, is a metric that gives more importance to precision than recall. This means that it penalizes false positives more than false negatives, which is not desirable for imbalanced data where the minority class is more important. F score with higher recall weighting than precision, or F2 score, is a metric that gives more importance to recall than precision. This means that it penalizes false negatives more than false positives, which might be suitable for some imbalanced data problems, but not for the logo detection problem. In this problem, both false positives and false negatives are equally important, as we want to accurately identify the presence or absence of a logo in an image. Therefore, the F1 score is a better metric than the F2 score. References:

Tour of Evaluation Metrics for Imbalanced Classification

Metrics for imbalanced data (simply explained)

Federated learning is a machine learning technique that enables organizations to train AI models on decentralized data without centralizing or sharing it1. It allows data privacy, continual learning, and better performance on end-user devices2. Federated learning works by sending the model parameters to the devices, where they are updated locally on the device’s data, and then aggregating the updated parameters on a central server to form a global model3. This way, the data never leaves the device and the model can learn from a large and diverse dataset.

Federated learning is suitable for the use case of building an ML-based biometric authentication for the bank’s mobile app that verifies a customer’s identity based on their fingerprint. Fingerprints are considered highly sensitive personal information and cannot be downloaded and stored into the bank databases. By using federated learning, the bank can train and deploy an ML model that can recognize fingerprints without compromising the data privacy of the customers. The model can also adapt to the variations and changes in the fingerprints over time and improve its accuracy and reliability. Therefore, federated learning is the best learning strategy for this use case.

The best option for creating a Dataflow pipeline for real-time anomaly detection is to load the model directly into the Dataflow job as a dependency, and use it for prediction. This option has the following advantages:

It minimizes the serving latency, as the model prediction logic is executed within the same Dataflow pipeline that ingests and processes the data. There is no need to invoke external services or containers, which can introduce network overhead and latency.

It simplifies the deployment and management of the model, as the model is packaged with the Dataflow job and does not require a separate service or container. The model can be updated by redeploying the Dataflow job with a new model version.

It leverages the scalability and reliability of Dataflow, as the model prediction logic can scale up or down with the data volume and handle failures and retries automatically.

The other options are less optimal for the following reasons:

Option A: Containerizing the model prediction logic in Cloud Run, which is invoked by Dataflow, introduces additional latency and complexity. Cloud Run is a serverless platform that runs stateless containers, which means that the model prediction logic needs to be initialized and loaded every time a request is made. This can increase the cold start latency and reduce the throughput. Moreover, Cloud Run has a limit on the number of concurrent requests per container, which can affect the scalability of the model prediction logic. Additionally, this option requires managing two separate services: the Dataflow pipeline and the Cloud Run container.

Option C: Deploying the model to a Vertex AI endpoint, and invoking this endpoint in the Dataflow job, also introduces additional latency and complexity. Vertex AI is a managed service that provides various tools and features for machine learning, such as training, tuning, serving, and monitoring. However, invoking a Vertex AI endpoint from a Dataflow job requires making an HTTP request, which can incur network overhead and latency. Moreover, this option requires managing two separate services: the Dataflow pipeline and the Vertex AI endpoint.

Option D: Deploying the model in a TFServing container on Google Kubernetes Engine, and invoking it in the Dataflow job, also introduces additional latency and complexity. TFServing is a high-performance serving system for TensorFlow models, which can handle multiple versions and variants of a model. However, invoking a TFServing container from a Dataflow job requires making a gRPC or REST request, which can incur network overhead and latency. Moreover, this option requires managing two separate services: the Dataflow pipeline and the Google Kubernetes Engine cluster.

References:

[Dataflow documentation]

[TensorFlow documentation]

[Cloud Run documentation]

[Vertex AI documentation]

[TFServing documentation]

 Vertex AI Platform is a unified platform for building and deploying ML models on Google Cloud. It supports both custom and AutoML models, and provides various tools and services for ML development, such as Vertex Pipelines, Vertex Vizier, Vertex Explainable AI, and Vertex Feature Store. Vertex AI Platform allows users to train their TensorFlow models using distributed training, which can speed up the training process and handle large datasets. Vertex AI Platform also minimizes code refactoring and infrastructure overhead, as it is compatible with TensorFlow Estimators and handles the provisioning, configuration, and scaling of the training resources automatically. The other options are not as suitable for this scenario. Dataproc is a service that allows users to create and run data processing pipelines using Apache Spark and Hadoop, but it is not designed for TensorFlow model training. Managed Instance Groups are a feature that allows users to create and manage groups of identical compute instances, but they require more configuration and management than Vertex AI Platform. Kubeflow Pipelines are a tool that allows users to create and run ML workflows on Google Kubernetes Engine, but they involve more complexity and code changes than Vertex AI Platform. References:

Vertex AI Platform documentation

Distributed training with Vertex AI Platform

This answer is correct because it uses a regression model to estimate the number of passengers at each shuttle station, which is a continuous variable. A tree-based regression model can handle both numerical and categorical features, such as the time of day, the location of the station, and the weather conditions. Based on the predicted number of passengers, the organization can dispatch a shuttle that has enough capacity and provide a map that shows the required stops. This way, the organization can optimize the shuttle service route and reduce the waiting time and fuel consumption. References:

[Tree-based regression models]

The best option to serve the model while optimizing cost, user experience, and ease of management is to deploy the model to Vertex AI Prediction, which is a managed service that can scale up or down according to the demand and provide low latency and high availability. Vertex AI Prediction can also handle TensorFlow models natively, without requiring any additional steps or conversions. By using batch prediction, the model can process large volumes of data efficiently and periodically, without affecting the user experience. The data can be read from Cloud Bigtable, which is a scalable and performant NoSQL database that can store user data in a flexible schema. The predictions can then be pushed to Cloud SQL, which is a fully managed relational database that can store the predictions in a structured format and enable easy querying and analysis. This option also simplifies the management of the model and the data, as it leverages the existing Google Cloud services and does not require any additional infrastructure or code.

The other options are not optimal for the following reasons:

A. Importing the model into BigQuery ML is not a good option, as it requires converting the TensorFlow model into a format that BigQuery ML can understand, which can introduce errors and reduce the performance. Moreover, BigQuery ML is not designed for serving real-time predictions, but rather for training and evaluating models using SQL queries. Reading and writing data from BigQuery and Cloud SQL can also incur additional costs and latency, as they are both relational databases that require schema definition and data transformation.

C. Embedding the model in the mobile application is not a good option, as it increases the size and complexity of the application, and requires updating the application every time the model changes. Moreover, it exposes the model to the users, which can pose security and privacy risks, as well as potential misuse or abuse. Additionally, it does not leverage the benefits of the cloud, such as scalability, reliability, and performance.

D. Embedding the model in the streaming Dataflow pipeline is not a good option, as it requires building and maintaining a custom pipeline that can handle the model inference and data processing. This can increase the development and operational costs and complexity, as well as the potential for errors and failures. Moreover, it does not take advantage of the batch prediction feature of Vertex AI Prediction, which can optimize the resource utilization and cost efficiency.

References:

Professional ML Engineer Exam Guide

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Google Cloud launches machine learning engineer certification

Vertex AI Prediction documentation

Cloud Bigtable documentation

Cloud SQL documentation

Sampled Shapley is a fast and scalable approximation of the Shapley value, which is a game-theoretic concept that measures the contribution of each feature to the model prediction. Sampled Shapley is suitable for online prediction requests, as it can return feature attributions with minimal latency. The path count parameter controls the number of samples used to estimate the Shapley value, and a lower value means faster computation. Integrated Gradients is another explanation method that computes the average gradient along the path from a baseline input to the actual input. Integrated Gradients is more accurate than Sampled Shapley, but also more computationally intensive. Therefore, it is not recommended for online prediction requests, especially with a high path count. Prediction drift is the change in the distribution of feature values or labels over time. It can affect the performance and accuracy of the model, and may require retraining or redeploying the model. Vertex AI Model Monitoring allows you to monitor prediction drift on your deployed models and endpoints, and set up alerts and notifications when the drift exceeds a certain threshold. You can specify an email address to receive the notifications, and use the information to retrigger the training pipeline and deploy an updated version of your model. This is the most direct and convenient way to achieve your goal. Training-serving skew is the difference between the data used for training the model and the data used for serving the model. It can also affect the performance and accuracy of the model, and may indicate data quality issues or model staleness. Vertex AI Model Monitoring allows you to monitor training-serving skew on your deployed models and endpoints, and set up alerts and notifications when the skew exceeds a certain threshold. However, this is not relevant to the question, as the question is about the feature attributions of the model, not the data distribution. References:

Vertex AI: Explanation methods

Vertex AI: Configuring explanations

Vertex AI: Monitoring prediction drift

Vertex AI: Monitoring training-serving skew

 The best option for developing an image classification model by using a large dataset that contains labeled images in a Cloud Storage bucket is to import the labeled images as a managed dataset in Vertex AI and use AutoML to train the model. This option allows you to leverage the power and simplicity of Google Cloud to create and deploy a high-quality image classification model with minimal code and configuration. Vertex AI is a unified platform for building and deploying machine learning solutions on Google Cloud. Vertex AI can create a managed dataset from a Cloud Storage bucket that contains labeled images, which can be used to train an AutoML model. AutoML is a service that can automatically build and optimize machine learning models for various tasks, such as image classification, object detection, natural language processing, and tabular data analysis. AutoML can handle the complex aspects of machine learning, such as feature engineering, model architecture, hyperparameter tuning, and model evaluation. AutoML can also evaluate, deploy, and monitor the image classification model, and provide online or batch predictions. By using Vertex AI and AutoML, users can develop an image classification model by using a large dataset with ease and efficiency.

The other options are not as good as option C, for the following reasons:

Option A: Using Vertex AI Pipelines with the Kubeflow Pipelines SDK to create a pipeline that reads the images from Cloud Storage and trains the model would require more skills and steps than using Vertex AI and AutoML. Vertex AI Pipelines is a service that can orchestrate machine learning workflows using Vertex AI. Vertex AI Pipelines can run preprocessing and training steps on custom Docker images, and evaluate, deploy, and monitor the machine learning model. Kubeflow Pipelines SDK is a Python library that can create and run pipelines on Vertex AI Pipelines or on Kubeflow, an open-source platform for machine learning on Kubernetes. However, using Vertex AI Pipelines and Kubeflow Pipelines SDK would require writing code, building Docker images, defining pipeline components and steps, and managing the pipeline execution and artifacts. Moreover, Vertex AI Pipelines and Kubeflow Pipelines SDK are not specialized for image classification, and users would need to use other libraries or frameworks, such as TensorFlow or PyTorch, to build and train the image classification model.

Option B: Using Vertex AI Pipelines with TensorFlow Extended (TFX) to create a pipeline that reads the images from Cloud Storage and trains the model would require more skills and steps than using Vertex AI and AutoML. TensorFlow Extended (TFX) is a framework that can create and run end-to-end machine learning pipelines on TensorFlow, a popular library for building and training deep learning models. TFX can preprocess the data, train and evaluate the model, validate and push the model, and serve the model for online or batch predictions. However, using Vertex AI Pipelines and TFX would require writing code, building Docker images, defining pipeline components and steps, and managing the pipeline execution and artifacts. Moreover, TFX is not optimized for image classification, and users would need to use other libraries or tools, such as TensorFlow Data Validation, TensorFlow Transform, and TensorFlow Hub, to handle the image data and the model architecture.

Option D: Converting the image dataset to a tabular format using Dataflow, loading the data into BigQuery, and using BigQuery ML to train the model would not handle the image data properly and could result in a poor model performance. Dataflow is a service that can create scalable and reliable pipelines to process large volumes of data from various sources. Dataflow can preprocess the data by using Apache Beam, a programming model for defining and executing data processing workflows. BigQuery is a serverless, scalable, and cost-effective data warehouse that can perform fast and interactive queries on large datasets. BigQuery ML is a service that can create and train machine learning models by using SQL queries on BigQuery. However, converting the image data to a tabular format would lose the spatial and semantic information of the images, which are essential for image classification. Moreover, BigQuery ML is not specialized for image classification, and users would need to use other tools or techniques, such as feature hashing, embedding, or one-hot encoding, to handle the categorical features.

Auto scaling is a feature that allows you to automatically adjust the number of prediction nodes based on the traffic and load of your deployed model1. However, auto scaling depends on the CPU utilization of your prediction nodes, which is the percentage of CPU resources used by your model server1. If your CPU utilization is low, even during periods of high load, it means that your model server is not fully utilizing the available CPU resources, and thus auto scaling will not trigger more replicas2.

One possible reason for low CPU utilization is that your model server is using a single worker process to handle prediction requests3. A worker process is a subprocess that runs your model code and handles prediction requests3. If you have only one worker process, it can only handle one request at a time, which can lead to dropped requests when the traffic is high3. To increase the CPU utilization and the throughput of your model server, you can increase the number of worker processes, which will allow your model server to handle multiple requests in parallel3.

To increase the number of workers in your model server, you need to modify your custom model server code and use the --workers flag to specify the number of worker processes you want to use3. For example, if you are using a Gunicorn server, you can use the following command to start your model server with four worker processes:

gunicorn --bind :$PORT --workers 4 --threads 1 --timeout 60 main:app

By increasing the number of workers in your model server, you can increase the CPU utilization of your prediction nodes, and thus enable auto scaling to scale beyond one replica.

The other options are not suitable for your scenario, because they either do not address the root cause of low CPU utilization, such as attaching a GPU or scheduling scaling, or they do not enable auto scaling, such as increasing the minReplicaCount, which is a fixed number of nodes that will always run regardless of the traffic1.

References:

Scaling prediction nodes | Vertex AI | Google Cloud

Troubleshooting | Vertex AI | Google Cloud

Using a custom prediction routine with online prediction | Vertex AI | Google Cloud

According to the official exam guide1, one of the skills assessed in the exam is to “design, build, and productionalize ML models to solve business challenges using Google Cloud technologies”. The Vertex AI Vision Occupancy Analytics model2 is a specialized pre-built vision model that lets you count people or vehicles given specific inputs you add in video frames. It provides advanced features such as active zones counting, line crossing counting, and dwelling detection. This model is suitable for the use case of detecting the number of customers waiting for service in near real time. You can easily create and deploy an occupancy analytics application using Vertex AI Vision3. The other options are not relevant or optimal for this scenario. References:

Professional ML Engineer Exam Guide

Occupancy analytics guide

Create an occupancy analytics app with BigQuery forecasting

Google Professional Machine Learning Certification Exam 2023

Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

Medical entity extraction is a task that involves identifying and classifying medical terms or concepts from unstructured textual data, such as electronic health records, clinical notes, or research papers. Medical entity extraction can help with various use cases, such as information retrieval, knowledge discovery, decision support, and data analysis1.

One possible approach to perform medical entity extraction is to use a BERT-based model to fine-tune a medical entity extraction model. BERT (Bidirectional Encoder Representations from Transformers) is a pre-trained language model that can capture the contextual information from both left and right sides of a given token2. BERT can be fine-tuned on a specific downstream task, such as medical entity extraction, by adding a task-specific layer on top of the pre-trained model and updating the model parameters with a small amount of labeled data3.

A BERT-based model can achieve high performance on medical entity extraction by leveraging the large-scale pre-training on general-domain corpora and the fine-tuning on domain-specific data. For example, Nesterov and Umerenkov4 proposed a novel method of doing medical entity extraction from electronic health records as a single-step multi-label classification task by fine-tuning a transformer model pre-trained on a large EHR dataset. They showed that their model can achieve human-level quality for most frequent entities.

References:

1: Medical Named Entity Recognition from Un-labelled Medical Records based on Pre-trained Language Models and Domain Dictionary | Data Intelligence | MIT Press

2: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

3: Fine-tuning BERT for Medical Entity Extraction

4: Distantly supervised end-to-end medical entity extraction from electronic health records with human-level quality

To organize the artifacts for dozens of pipelines, you should store the parameters in Vertex ML Metadata, store the models’ source code in GitHub, and store the models’ binaries in Cloud Storage. This option has the following advantages:

Vertex ML Metadata is a service that helps you track and manage the metadata of your ML workflows, such as datasets, models, metrics, and parameters1. It can also help you with data lineage, model versioning, and model performance monitoring2.

GitHub is a popular platform for hosting and collaborating on code repositories. It can help you manage the source code of your models, as well as the configuration files, scripts, and notebooks that are part of your ML pipelines3.

Cloud Storage is a scalable and durable object storage service that can store any type of data, including model binaries4. It can also integrate with other services, such as Vertex AI, Cloud Functions, and Cloud Run, to enable easy deployment and serving of your models5.

References:

1: Introduction to Vertex ML Metadata | Vertex AI | Google Cloud

2: Manage metadata for ML workflows | Vertex AI | Google Cloud

3: GitHub - Where the world builds software

4: Cloud Storage | Google Cloud

5: Deploying models | Vertex AI | Google Cloud

The best option for optimizing the data processing pipeline for run time and compute resources utilization is to embed the augmentation functions dynamically in the tf.Data pipeline. This option has the following advantages:

It allows the data augmentation to be performed on the fly, without creating or storing additional copies of the data. This saves storage space and reduces the data transfer time.

It leverages the parallelism and performance of the tf.Data API, which can efficiently apply the augmentation functions to multiple batches of data in parallel, using multiple CPU cores or GPU devices. The tf.Data API also supports various optimization techniques, such as caching, prefetching, and autotuning, to improve the data processing speed and reduce the latency.

It integrates seamlessly with the TensorFlow and Keras models, which can consume the tf.Data datasets as inputs for training and evaluation. The tf.Data API also supports various data formats, such as images, text, audio, and video, and various data sources, such as files, databases, and web services.

The other options are less optimal for the following reasons:

Option B: Embedding the augmentation functions dynamically as part of Keras generators introduces some limitations and overhead. Keras generators are Python generators that yield batches of data for training or evaluation. However, Keras generators are not compatible with the tf.distribute API, which is used to distribute the training across multiple devices or machines. Moreover, Keras generators are not as efficient or scalable as the tf.Data API, as they run on a single Python thread and do not support parallelism or optimization techniques.

Option C: Using Dataflow to create all possible augmentations, and store them as TFRecords introduces additional complexity and cost. Dataflow is a fully managed service that runs Apache Beam pipelines for data processing and transformation. However, using Dataflow to create all possible augmentations requires generating and storing a large number of augmented images, which can consume a lot of storage space and incur storage and network costs. Moreover, using Dataflow to create the augmentations requires writing and deploying a separate Dataflow pipeline, which can be tedious and time-consuming.

Option D: Using Dataflow to create the augmentations dynamically per training run, and stage them as TFRecords introduces additional complexity and latency. Dataflow is a fully managed service that runs Apache Beam pipelines for data processing and transformation. However, using Dataflow to create the augmentations dynamically per training run requires running a Dataflow pipeline every time the model is trained, which can introduce latency and delay the training process. Moreover, using Dataflow to create the augmentations requires writing and deploying a separate Dataflow pipeline, which can be tedious and time-consuming.

References:

[tf.data: Build TensorFlow input pipelines]

[Image augmentation | TensorFlow Core]

[Dataflow documentation]

AutoML Natural Language is a service that allows you to quickly build, test and deploy natural language processing (NLP) models without needing to have expertise in NLP or machine learning. You can use it to train a classifier on your corpus of written support cases, and then use the AutoML API to perform classification on new requests. Once the model is trained, it can be deployed as a REST API. This allows the classifier to be integrated into your pipeline and be easily consumed by other systems.

Option A is incorrect because using AI Platform notebooks to perform a Lasso regression analysis on your model, which will eliminate features that do not provide a strong signal, is not a suitable way to determine which customer attribute has the most predictive power for each prediction served by the model. Lasso regression is a method of feature selection that applies a penalty to the coefficients of the linear model, and shrinks them to zero for irrelevant features1. However, this method assumes that the model is linear and additive, which may not be the case for a TensorFlow model. Moreover, this method does not provide feature attributions for each prediction, but rather for the entire dataset.

Option B is incorrect because streaming prediction results to BigQuery, and using BigQuery’s CORR(X1, X2) function to calculate the Pearson correlation coefficient between each feature and the target variable, is not a valid way to determine which customer attribute has the most predictive power for each prediction served by the model. The Pearson correlation coefficient is a measure of the linear relationship between two variables, ranging from -1 to 12. However, this method does not account for the interactions between features or the non-linearity of the model. Moreover, this method does not provide feature attributions for each prediction, but rather for the entire dataset.

Option C is correct because using the AI Explanations feature on AI Platform, and submitting each prediction request with the ‘explain’ keyword to retrieve feature attributions using the sampled Shapley method, is the best way to determine which customer attribute has the most predictive power for each prediction served by the model. AI Explanations is a service that allows you to get feature attributions for your deployed models on AI Platform3. Feature attributions are values that indicate how much each feature contributed to the prediction for a given instance4. The sampled Shapley method is a technique that uses the Shapley value, a game-theoretic concept, to measure the contribution of each feature to the prediction5. By using AI Explanations, you can get feature attributions for each prediction request, and identify the most important features for each customer.

Option D is incorrect because using the What-If tool in Google Cloud to determine how your model will perform when individual features are excluded, and ranking the feature importance in order of those that caused the most significant performance drop when removed from the model, is not a practical way to determine which customer attribute has the most predictive power for each prediction served by the model. The What-If tool is a tool that allows you to visualize and analyze your ML models and datasets. However, this method requires manually editing or removing features for each instance, and observing the change in the prediction. This method is not scalable or efficient, and may not capture the interactions between features or the non-linearity of the model.

References:

Lasso regression

Pearson correlation coefficient

AI Explanations overview

Feature attributions

Sampled Shapley method

[What-If tool overview]

The best option for analyzing large and complex datasets while minimizing computational resources is to use a combination of BigQuery and Vertex AI Workbench. BigQuery is a serverless, scalable, and cost-effective data warehouse that can perform fast and interactive queries on petabytes of data. BigQuery can calculate descriptive statistics such as mean, median, and mode by using SQL functions such as AVG, PERCENTILE_CONT, and MODE. Vertex AI Workbench is a managed service that provides an integrated development environment for data science and machine learning. Vertex AI Workbench allows users to create and run Jupyter notebooks on Google Cloud, and access various tools and libraries for data visualization and statistical analysis. Vertex AI Workbench can connect to BigQuery and use the results of the queries to create time plots and run statistical tests for hypothesis testing. By using BigQuery and Vertex AI Workbench, users can leverage the power and flexibility of Google Cloud to perform exploratory data analysis on large and complex datasets. References:

Preparing for Google Cloud Certification: Machine Learning Engineer, Course 2: Data Engineering for ML on Google Cloud, Week 1: Introduction to Data Engineering for ML

Google Cloud Professional Machine Learning Engineer Exam Guide, Section 1: Architecting low-code ML solutions, 1.1 Developing ML models by using BigQuery ML

Official Google Cloud Certified Professional Machine Learning Engineer Study Guide, Chapter 3: Data Engineering for ML, Section 3.2: BigQuery for ML

The best option for reducing the sensitivity of the dataset before training the model is to use the Cloud Data Loss Prevention (DLP) API to scan for sensitive data, and use Dataflow with the DLP API to encrypt sensitive values with Format Preserving Encryption. This option allows you to keep every column in the dataset, while protecting the sensitive data from unauthorized access or exposure. The Cloud DLP API can detect and classify various types of sensitive data, such as names, email addresses, phone numbers, credit card numbers, and more1. Dataflow can create scalable and reliable pipelines to process large volumes of data from BigQuery and other sources2. Format Preserving Encryption (FPE) is a technique that encrypts sensitive data while preserving its original format and length, which can help maintain the utility and validity of the data3. By using Dataflow with the DLP API, you can apply FPE to the sensitive values in the dataset, and store the encrypted data in BigQuery or another destination. You can also use the same pipeline to decrypt the data when needed, by using the same encryption key and method4.

The other options are not as suitable as option B, for the following reasons:

Option A: Using Dataflow to ingest the columns with sensitive data from BigQuery, and then randomize the values in each sensitive column, would reduce the sensitivity of the data, but also the utility and accuracy of the data. Randomization is a technique that replaces sensitive data with random values, which can prevent re-identification of the data, but also distort the distribution and relationships of the data3. This can affect the performance and quality of the ML model, especially if every column is critical to the model.

Option C: Using the Cloud DLP API to scan for sensitive data, and use Dataflow to replace all sensitive data by using the encryption algorithm AES-256 with a salt, would reduce the sensitivity of the data, but also the utility and validity of the data. AES-256 is a symmetric encryption algorithm that uses a 256-bit key to encrypt and decrypt data. A salt is a random value that is added to the data before encryption, to increase the randomness and security of the encrypted data. However, AES-256 does not preserve the format or length of the original data, which can cause problems when storing or processing the data. For example, if the original data is a 10-digit phone number, AES-256 would produce a much longer and different string, which can break the schema or logic of the dataset3.

Option D: Before training, using BigQuery to select only the columns that do not contain sensitive data, and creating an authorized view of the data so that sensitive values cannot be accessed by unauthorized individuals, would reduce the exposure of the sensitive data, but also the completeness and relevance of the data. An authorized view is a BigQuery view that allows you to share query results with particular users or groups, without giving them access to the underlying tables. However, this option assumes that you can identify the columns that do not contain sensitive data, which may not be easy or accurate. Moreover, this option would remove some columns from the dataset, which can affect the performance and quality of the ML model, especially if every column is critical to the model.

References:

Preparing for Google Cloud Certification: Machine Learning Engineer, Course 5: Responsible AI, Week 2: Privacy

Google Cloud Professional Machine Learning Engineer Exam Guide, Section 5: Developing responsible AI solutions, 5.2 Implementing privacy techniques

Official Google Cloud Certified Professional Machine Learning Engineer Study Guide, Chapter 9: Responsible AI, Section 9.4: Privacy

De-identification techniques

Cloud Data Loss Prevention (DLP) API

Dataflow

Using Dataflow and Sensitive Data Protection to securely tokenize and import data from a relational database to BigQuery

[AES encryption]

[Salt (cryptography)]

[Authorized views]

 BigQuery ML allows you to build and run machine learning models using SQL queries directly within BigQuery, which is one of the simplest approaches because it doesn't require setting up an external environment like Vertex AI or managing infrastructure.

 AutoML regression is more appropriate for predicting customer lifetime value (CLV) compared to ARIMA, which is typically used for time series forecasting (e.g., sales over time, stock prices, etc.). CLV prediction involves understanding complex relationships between customer behavior and value, which is best captured by a regression model.

 Using BigQuery Studio and running a CREATE MODEL statement to build an AutoML regression model offers the simplicity you're looking for because it automates much of the feature engineering, model selection, and hyperparameter tuning.

 The other options involving ARIMA models (A and B) are not appropriate for CLV, and setting up a Vertex AI Workbench notebook (D) introduces unnecessary complexity for this task.

You are implementing a batch inference ML pipeline in Google Cloud. The model was developed by using TensorFlow and is stored in SavedModel format in Cloud Storage. You need to apply the model to a historical dataset that is stored in a BigQuery table. You want to perform inference with minimal effort. What should you do?

A. Import the TensorFlow model by using the create model statement in BigQuery ML. Apply the historical data to the TensorFlow model.

B. Export the historical data to Cloud Storage in Avro format. Configure a Vertex Al batch prediction job to generate predictions for the exported data.

C. Export the historical data to Cloud Storage in CSV format. Configure a Vertex Al batch prediction job to generate predictions for the exported data.

D. Configure and deploy a Vertex Al endpoint. Use the endpoint to get predictions from the historical data in BigQuery.

Answer: B

 Vertex AI batch prediction is the most appropriate and efficient way to apply a pre-trained model like TensorFlow’s SavedModel to a large dataset, especially for batch processing.

 The Vertex AI batch prediction job works by exporting your dataset (in this case, historical data from BigQuery) to a suitable format (like Avro or CSV) and then processing it in Cloud Storage where the model is stored.

 Avro format is recommended for large datasets as it is highly efficient for data storage and is optimized for read/write operations in Google Cloud, which is why option B is correct.

 Option A suggests using BigQuery ML for inference, but it does not support running arbitrary TensorFlow models directly within BigQuery ML. Hence, BigQuery ML is not a valid option for this particular task.

 Option C (exporting to CSV) is a valid alternative but is less efficient compared to Avro in terms of performance.

 Option D suggests deploying a Vertex AI endpoint, which is better suited for real-time inference rather than batch inference. Since the question asks for batch inference, B is the best answer.

BigQuery ML is a service that allows you to create and train ML models using SQL queries. You can use BigQuery ML to train an AutoML regression model, which is a type of model that automatically selects the best features and architecture for your data. You can also specify Vertex AI as the model registry, which is a service that allows you to store and manage your ML models. By using Vertex AI as the model registry, you can easily deploy your model to a Vertex AI endpoint, which is a service that allows you to serve your ML models online and scale them automatically. By using BigQuery ML, Vertex AI model registry, and Vertex AI endpoint, you can deploy your model for online prediction as quickly as possible, without having to export, import, or retrain your model. References:

BigQuery ML documentation

Vertex AI documentation

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Option A is incorrect because converting each categorical value into an integer value is not a good way to encode categorical values with high cardinality. This method implies an ordinal relationship between the categories, which may not be true. For example, assigning the values 1, 2, and 3 to the categories “red”, “green”, and “blue” does not make sense, as there is no inherent order among these colors1.

Option B is correct because converting the categorical string data to one-hot hash buckets is a suitable way to encode categorical values with high cardinality. This method uses a hash function to map each category to a fixed-length vector of binary values, where only one element is 1 and the rest are 0. This method preserves the sparsity and independence of the categories, and reduces the dimensionality of the input space2.

Option C is incorrect because mapping the categorical variables into a vector of boolean values is not a valid way to encode categorical values with high cardinality. This method implies that each category can be represented by a combination of true/false values, which may not be possible for a large number of categories. For example, if there are 10,000 categories, then there are 2^10,000 possible combinations of boolean values, which is impractical to store and process3.

Option D is incorrect because converting each categorical value into a run-length encoded string is not a useful way to encode categorical values with high cardinality. This method compresses a string by replacing consecutive repeated characters with the character and the number of repetitions. For example, “AAAABBBCC” becomes “A4B3C2”. This method does not reduce the dimensionality of the input space, and does not preserve the semantic meaning of the categories4.

References:

Encoding categorical features

One-hot hash buckets

Boolean vector

Run-length encoding

The best option for dealing with the missing categorical variable in the test set is to apply one-hot encoding on the categorical variables in the test data. This option has the following advantages:

It ensures the consistency and compatibility of the data format for the ML model, as the one-hot encoding transforms the categorical variables into binary vectors that can be easily processed by the model. By applying one-hot encoding on the categorical variables in the test data, you can match the number and order of the features in the test data with the training data, and avoid any errors or discrepancies in the model prediction.

It preserves the information and relevance of the data for the ML model, as the one-hot encoding creates a separate feature for each possible value of the categorical variable, and assigns a value of 1 to the feature corresponding to the actual value of the variable, and 0 to the rest. By applying one-hot encoding on the categorical variables in the test data, you can retain the original meaning and importance of the categorical variable, and avoid any loss or distortion of the data.

The other options are less optimal for the following reasons:

Option A: Randomly redistributing the data, with 70% for the training set and 30% for the test set, introduces additional complexity and risk. This option requires reshuffling and splitting the data again, which can be tedious and time-consuming. Moreover, this option may not guarantee that the missing categorical variable will be present in the test set, as it depends on the randomness of the data distribution. Furthermore, this option may affect the quality and validity of the ML model, as it may change the data characteristics and patterns that the model has learned from the original training set.

Option B: Using sparse representation in the test set introduces additional overhead and inefficiency. This option requires converting the categorical variables in the test set into sparse vectors, which are vectors that have mostly zero values and only store the indices and values of the non-zero elements. However, using sparse representation in the test set may not be compatible with the ML model, as the model expects the input data to have the same format and dimensionality as the training data, which uses one-hot encoding. Moreover, using sparse representation in the test set may not be efficient or scalable, as it requires additional computation and memory to store and process the sparse vectors.

Option D: Collecting more data representing all categories introduces additional cost and delay. This option requires obtaining and labeling more data that contains the missing categorical variable, which can be expensive and time-consuming. Moreover, this option may not be feasible or necessary, as the missing categorical variable may not be available or relevant for the test data, depending on the data source or the business problem.

According to the official exam guide1, one of the skills assessed in the exam is to “design, build, and productionalize ML models to solve business challenges using Google Cloud technologies”. Vertex AI AutoML Forecasting2 is a service that allows you to train and deploy custom time-series forecasting models for batch prediction. Vertex AI AutoML Forecasting simplifies the model development process by providing a graphical user interface and a no-code approach. You can use Vertex AI AutoML Forecasting to train a model by using your tabular data, and specify the target variable, the covariates, and the time variable. Vertex AI AutoML Forecasting automatically handles the feature engineering, model selection, and hyperparameter tuning. Therefore, option D is the best way to maximize the speed of model development and testing for the given use case. The other options are not relevant or optimal for this scenario. References:

Professional ML Engineer Exam Guide

Vertex AI AutoML Forecasting

Google Professional Machine Learning Certification Exam 2023

Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

Deploying the model on GKE with a custom YAML manifest allows maximum control over infrastructure and latency, aligning with the need for low inference time and internal model use. Vertex AI's one-click deployment (Option A) limits control, and deploying on Vertex AI (Option C) doesn’t allow for as much customization as a GKE setup.

=================

To configure a model retraining policy that minimizes cost, you should follow these steps:

Download the weather data each week, and download the flu data each month. This way, you can keep your data up to date with the latest information available, without downloading unnecessary or redundant data.

Deploy the model to a Vertex AI endpoint with feature drift monitoring. This feature allows you to detect when the distribution of the input data changes significantly from the training data, which could affect the model performance1.

Retrain the model if a monitoring alert is detected. This way, you can update your model only when needed, instead of retraining it on a fixed schedule, which could incur more cost and time.

References:

1: Monitor models for feature drift | Vertex AI | Google Cloud

The most likely problem is that the tables that you created to hold your training and validation records share some records, and you may not be using all the data in your initial table. This is because the RAND() function generates a random number between 0 and 1 for each row, and the probability of a row being in both the training and validation tables is 0.2 * 0.8 = 0.16, which is not negligible. This means that some of the records that you use to validate your model are also used to train your model, which can lead to overfitting and poor generalization. Moreover, the probability of a row being in neither the training nor the validation table is 0.2 * 0.2 = 0.04, which means that you are wasting some of the data in your initial table and reducing the size of your datasets. A better way to split your data into training and validation sets is to use a hash function on a unique identifier column, such as the following queries:

CREATE OR REPLACE TABLE ‘myproject.mydataset.training‘ AS (SELECT * FROM ‘myproject.mydataset.mytable‘ WHERE MOD(FARM_FINGERPRINT(id), 10) < 8); CREATE OR REPLACE TABLE ‘myproject.mydataset.validation‘ AS (SELECT * FROM ‘myproject.mydataset.mytable‘ WHERE MOD(FARM_FINGERPRINT(id), 10) >= 8);

This way, you can ensure that each row has a fixed 80% chance of being in the training table and a 20% chance of being in the validation table, without any overlap or omission.

References:

Professional ML Engineer Exam Guide

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

Google Cloud launches machine learning engineer certification

BigQuery ML: Splitting data for training and testing

BigQuery: FARM_FINGERPRINT function

 According to the official exam guide1, one of the skills assessed in the exam is to “automate and orchestrate ML pipelines using Cloud Composer”. Cloud Composer2 is a fully managed workflow orchestration service that uses Apache Airflow to create, schedule, monitor, and manage workflows. Cloud Composer allows you to build custom training pipelines for deep learning-based models and integrate them with other Google Cloud services. You can also use Cloud Composer to implement model interpretability techniques, such as feature attributions, explainable AI, or model debugging3. The other options are not relevant or optimal for this scenario. References:

Professional ML Engineer Exam Guide

Cloud Composer

Model interpretability with Cloud Composer

Google Professional Machine Learning Certification Exam 2023

Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

AutoML Tables is a service that allows you to automatically build and deploy state-of-the-art machine learning models on structured data without writing code. You can use AutoML Tables to perform the following steps for the classification task:

Exploratory data analysis: AutoML Tables provides a graphical user interface (GUI) and a command-line interface (CLI) to explore your data, visualize statistics, and identify potential issues.

Feature selection: AutoML Tables automatically selects the most relevant features for your model based on the data schema and the target column. You can also manually exclude or include features, or create new features from existing ones using feature engineering.

Model building: AutoML Tables automatically builds and evaluates multiple machine learning models using different algorithms and architectures. You can also specify the optimization objective, the budget, and the evaluation metric for your model.

Training and hyperparameter tuning: AutoML Tables automatically trains and tunes your model using the best practices and techniques from Google’s research and engineering teams. You can monitor the training progress and the performance of your model on the GUI or the CLI.

Serving: AutoML Tables automatically deploys your model to a fully managed, scalable, and secure environment. You can use the GUI or the CLI to request predictions from your model, either online (synchronously) or offline (asynchronously).

References:

[AutoML Tables documentation]

[AutoML Tables overview]

[AutoML Tables how-to guides]

 Customer churn is a binary classification problem, where the target variable is whether a customer has churned or not. Therefore, a logistic regression model is more suitable than a linear regression model, which is used for regression problems. A logistic regression model can output the probability of a customer churning, which can be used to rank the customers by their churn risk and take appropriate actions1.

BigQuery ML is a service that allows you to create and execute machine learning models in BigQuery using standard SQL queries2. You can use BigQuery ML to create a logistic regression model for customer churn prediction by using the CREATE MODEL statement and specifying the LOGISTIC_REG model type3. You can use the historical customer data as the input table for the model, and specify the features and the label columns3.

Vertex AI Model Registry is a central repository where you can manage the lifecycle of your ML models4. You can import models from various sources, such as BigQuery ML, AutoML, or custom models, and assign them to different versions and aliases4. You can also deploy models to endpoints, which are resources that provide a service URL for online prediction.

By registering the BigQuery ML model in Vertex AI Model Registry, you can leverage the Vertex AI features to evaluate and monitor the model performance4. You can use Vertex AI Experiments to track and compare the metrics of different model versions, such as accuracy, precision, recall, and AUC. You can also use Vertex AI Explainable AI to generate feature attributions that show how much each input feature contributed to the model’s prediction.

The other options are not suitable for your scenario, because they either use the wrong model type, such as linear regression, or they do not use Vertex AI to evaluate the model performance, which would limit the insights and actions you can take based on the model results.

References:

Logistic Regression for Machine Learning

Introduction to BigQuery ML | Google Cloud

Creating a logistic regression model | BigQuery ML | Google Cloud

Introduction to Vertex AI Model Registry | Google Cloud

[Deploy a model to an endpoint | Vertex AI | Google Cloud]

[Vertex AI Experiments | Google Cloud]

 A predict request is a way to send data to a trained model and get predictions in return. A predict request can be written in different formats, such as JSON, protobuf, or gRPC, depending on the service and the platform that are used to host and serve the model. A predict request usually contains the following information:

The signature name: This is the name of the signature that defines the inputs and outputs of the model. A signature is a way to specify the expected format, type, and shape of the data that the model can accept and produce. A signature can be specified when exporting or saving the model, or it can be automatically inferred by the service or the platform. A model can have multiple signatures, but only one can be used for each predict request.

The instances: This is the data that is sent to the model for prediction. The instances can be a single instance or a batch of instances, depending on the size and shape of the data. The instances should match the input specification of the signature, such as the number, name, and type of the input tensors.

For the use case of training a text classification model, the correct way to write the predict request is D. data = json.dumps({“signature_name”: “serving_default”, “instances”: [[‘a’, ‘b’], [‘c’, ‘d’], [‘e’, ‘f’]]})

This option involves writing the predict request in JSON format, which is a common and convenient format for sending and receiving data over the web. JSON stands for JavaScript Object Notation, and it is a way to represent data as a collection of name-value pairs or an ordered list of values. JSON can be easily converted to and from Python objects using the json module.

This option also involves using the signature name “serving_default”, which is the default signature name that is assigned to the model when it is saved or exported without specifying a custom signature name. The serving_default signature defines the input and output tensors of the model based on the SignatureDef that is shown in the image. According to the SignatureDef, the model expects an input tensor called “text” that has a shape of (-1, 2) and a type of DT_STRING, and produces an output tensor called “softmax” that has a shape of (-1, 2) and a type of DT_FLOAT. The -1 in the shape indicates that the dimension can vary depending on the number of instances, and the 2 indicates that the dimension is fixed at 2. The DT_STRING and DT_FLOAT indicate that the data type is string and float, respectively.

This option also involves sending a batch of three instances to the model for prediction. Each instance is a list of two strings, such as [‘a’, ‘b’], [‘c’, ‘d’], or [‘e’, ‘f’]. These instances match the input specification of the signature, as they have a shape of (3, 2) and a type of string. The model will process these instances and produce a batch of three predictions, each with a softmax output that has a shape of (1, 2) and a type of float. The softmax output is a probability distribution over the two possible classes that the model can predict, such as positive or negative sentiment.

Therefore, writing the predict request as data = json.dumps({“signature_name”: “serving_default”, “instances”: [[‘a’, ‘b’], [‘c’, ‘d’], [‘e’, ‘f’]]}) is the correct and valid way to send data to the text classification model and get predictions in return.

References:

[json — JSON encoder and decoder]

According to the official exam guide1, one of the skills assessed in the exam is to “configure and optimize model monitoring jobs”. Vertex AI Model Monitoring documentation states that “model monitoring helps you detect when your model’s performance degrades over time due to changes in the data that your model receives or returns” and that "you can configure model monitoring to send notifications to Pub/Sub when it detects anomalies or drift in your model’s predictions"2. Therefore, enabling model monitoring on the Vertex AI endpoint and configuring Pub/Sub to call the Cloud Function when feature drift is detected would help you keep the model up-to-date and minimize retraining costs. The other options are not relevant or optimal for this scenario. References:

Professional ML Engineer Exam Guide

Vertex AI Model Monitoring

Google Professional Machine Learning Certification Exam 2023

Latest Google Professional Machine Learning Engineer Actual Free Exam Questions

 The best way to distribute the training examples across the train-test-eval subsets while maintaining the 80-10-10 proportion is to use option C. This option ensures that each subset contains a balanced and representative sample of the different classes (Democrat and Republican) and the different authors. This way, the model can learn from a diverse and comprehensive set of articles and avoid overfitting or underfitting. Option C also avoids the problem of data leakage, which occurs when the same author appears in more than one subset, potentially biasing the model and inflating its performance. Therefore, option C is the most suitable technique for this use case.

 This answer is correct because it uses Firebase, a platform that provides a scalable and reliable notification system for mobile and web applications. Firebase Cloud Messaging (FCM) allows you to send messages and notifications to users across different devices and platforms. By registering each user with a user ID on the FCM server, you can target specific users based on their account balance predictions and send them personalized notifications when their balance is likely to drop below the $25 threshold. This way, you can provide a useful and timely feature for your customers and increase their engagement and retention. References:

[Firebase Cloud Messaging]

[Firebase Cloud Messaging: Send messages to specific devices]

 Labels are key-value pairs that you can attach to AI Platform resources such as jobs, models, and versions. Labels can help you organize your resources into descriptive categories that reflect your business needs. For example, you can use labels to indicate the owner, purpose, environment, or status of a resource. You can also use labels to filter the results when you list or monitor your resources on the Google Cloud Console or the Cloud SDK. Using labels can help you manage your resources in a clean and scalable way, without requiring separate projects or restrictive permissions.

References:

Using labels to organize AI Platform resources

Creating and managing labels

QUESTION 52

You are training a deep learning model for semantic image segmentation with reduced training time. While using a Deep Learning VM Image, you receive the following error: The resource 'projects/deeplearning-platforn/zones/europe-west4-c/acceleratorTypes/nvidia-tesla-k80' was not found. What should you do?

A. Ensure that you have GPU quota in the selected region.

B. Ensure that the required GPU is available in the selected region.

C. Ensure that you have preemptible GPU quota in the selected region.

D. Ensure that the selected GPU has enough GPU memory for the workload.

Answer: B

The error message indicates that the selected GPU type (nvidia-tesla-k80) is not available in the selected region (europe-west4-c). This can happen when the GPU type is not supported in the region, or when the GPU quota is exhausted in the region. To avoid this error, you should ensure that the required GPU is available in the selected region before creating a Deep Learning VM Image. You can use the following steps to check the GPU availability and quota:

To check the GPU availability, you can use the gcloud compute accelerator-types list command with the --filter flag to specify the GPU type and the region. For example, to check the availability of nvidia-tesla-k80 in europe-west4-c, you can run:

gcloud compute accelerator-types list --filter="name=nvidia-tesla-k80 AND zone:europe-west4-c"

If the command returns an empty result, it means that the GPU type is not supported in the region. You can either choose a different GPU type or a different region that supports the GPU type. You can use the same command without the --filter flag to list all the available GPU types and regions. For example, to list all the available GPU types in europe-west4-c, you can run:

gcloud compute accelerator-types list --filter="zone:europe-west4-c"

To check the GPU quota, you can use the gcloud compute regions describe command with the --format flag to specify the region and the quota metric. For example, to check the quota for nvidia-tesla-k80 in europe-west4-c, you can run:

gcloud compute regions describe europe-west4-c --format="value(quotas.NVIDIA_K80_GPUS)"

If the command returns a value of 0, it means that the GPU quota is exhausted in the region. You can either request more quota from Google Cloud or choose a different region that has enough quota for the GPU type.

References:

Troubleshooting | Deep Learning VM Images | Google Cloud

Checking GPU availability

Checking GPU quota

The best option for parametrizing the model training in Kubeflow Pipelines is to add a ContainerOp to the pipeline that spins a Dataproc cluster, runs a transformation, and then saves the transformed data in Cloud Storage. This option has the following advantages:

It allows the data transformation to be performed as part of the Kubeflow Pipeline, which can ensure the consistency and reproducibility of the data processing and the model training. By adding a ContainerOp to the pipeline, you can define the parameters and the logic of the data transformation step, and integrate it with the other steps of the pipeline, such as the model training and evaluation.

It leverages the scalability and performance of Dataproc, which is a fully managed service that runs Apache Spark and Apache Hadoop clusters on Google Cloud. By spinning a Dataproc cluster, you can run the PySpark transformation on the Parquet files stored in the Hive table, and take advantage of the parallelism and speed of Spark. Dataproc also supports various features and integrations, such as autoscaling, preemptible VMs, and connectors to other Google Cloud services, that can optimize the data processing and reduce the cost.

It simplifies the data storage and access, as the transformed data is saved in Cloud Storage, which is a scalable, durable, and secure object storage service. By saving the transformed data in Cloud Storage, you can avoid the overhead and complexity of managing the data in the Hive table or the Parquet files. Moreover, you can easily access the transformed data from Cloud Storage, using various tools and frameworks, such as TensorFlow, BigQuery, or Vertex AI.

The other options are less optimal for the following reasons:

Option A: Removing the data transformation step from the pipeline eliminates the parametrization of the model training, as the data processing and the model training are decoupled and independent. This option requires running the PySpark transformation separately from the Kubeflow Pipeline, which can introduce inconsistency and unreproducibility in the data processing and the model training. Moreover, this option requires managing the data in the Hive table or the Parquet files, which can be cumbersome and inefficient.

Option B: Containerizing the PySpark transformation step, and adding it to the pipeline introduces additional complexity and overhead. This option requires creating and maintaining a Docker image that can run the PySpark transformation, which can be challenging and time-consuming. Moreover, this option requires running the PySpark transformation on a single container, which can be slow and inefficient, as it does not leverage the parallelism and performance of Spark.

Option D: Deploying Apache Spark at a separate node pool in a Google Kubernetes Engine cluster, and adding a ContainerOp to the pipeline that invokes a corresponding transformation job for this Spark instance introduces additional complexity and cost. This option requires creating and managing a separate node pool in a Google Kubernetes Engine cluster, which is a fully managed service that runs Kubernetes clusters on Google Cloud. Moreover, this option requires deploying and running Apache Spark on the node pool, which can be tedious and costly, as it requires configuring and maintaining the Spark cluster, and paying for the node pool usage.

TFRecords are a binary file format that can store large amounts of data efficiently. By converting the images to TFRecords and storing them in a Cloud Storage bucket, you can reduce the data size and improve the data transfer speed. You can then read the TFRecords by using the tf.data.TFRecordDataset function, which creates a dataset of tensors from the TFRecord files. This way, you can read images at scale during training while minimizing data I/O bottlenecks. References:

TFRecord documentation

tf.data.TFRecordDataset documentation

Preparing for Google Cloud Certification: Machine Learning Engineer Professional Certificate

A caching layer is essential to reduce database access time, meeting the <100ms requirement. Caches store high-frequency, low-latency queries in memory, minimizing access delays caused by database lookups. While AlloyDB (Option B) provides performance benefits, a caching layer is more efficient and cost-effective for this purpose. BigQuery ML (Option A) is less ideal for real-time personalized responses due to access speed, and vector embeddings (Option C) are not needed unless semantic search is a requirement.

=================

Option A is incorrect because training a time-series model to predict the machines’ performance values, and configuring an alert if a machine’s actual performance values significantly differ from the predicted performance values, is not the best way to build a predictive maintenance solution that uses monitoring data from the VMs to detect potential failures and then alerts the service desk team. This option assumes that the performance values follow a predictable pattern, which may not be the case for complex systems. Moreover, this option does not use any historical incident data, which may contain useful information for identifying failures. Furthermore, this option does not involve any model evaluation or validation, which are essential steps for ensuring the quality and reliability of the model.

Option B is correct because implementing a simple heuristic (e.g., based on z-score) to label the machines’ historical performance data, and training a model to predict anomalies based on this labeled dataset, is a reasonable way to build a predictive maintenance solution that uses monitoring data from the VMs to detect potential failures and then alerts the service desk team. This option uses a simple and fast method to label the historical performance data, which is necessary for supervised learning. A z-score is a measure of how many standard deviations a value is away from the mean of a distribution1. By using a z-score, we can label the performance values that are unusually high or low as anomalies, which may indicate failures. Then, we can train a model to learn the patterns of normal and anomalous performance values, and use it to predict anomalies on new data. We can also evaluate and validate the model using metrics such as precision, recall, or F1-score, and compare it with other models or methods.

Option C is incorrect because developing a simple heuristic (e.g., based on z-score) to label the machines’ historical performance data, and testing this heuristic in a production environment, is not a safe way to build a predictive maintenance solution that uses monitoring data from the VMs to detect potential failures and then alerts the service desk team. This option does not involve any model training or evaluation, which are essential steps for ensuring the quality and reliability of the solution. Moreover, this option does not test the heuristic on a separate dataset, such as a validation or test set, before deploying it to production, which may lead to errors or failures in the production environment.

Option D is incorrect because hiring a team of qualified analysts to review and label the machines’ historical performance data, and training a model based on this manually labeled dataset, is not a feasible way to build a predictive maintenance solution that uses monitoring data from the VMs to detect potential failures and then alerts the service desk team. This option may produce high-quality labels, but it is also costly, time-consuming, and prone to human errors or biases. Moreover, this option may not scale well with large or complex datasets, which may require more analysts or more time to label.

References:

Z-score

[Predictive maintenance]

[Anomaly detection]

[Time-series analysis]

[Model evaluation]

 The best option for building a recommendation system without any user event data is to use simple heuristics based on content metadata. This is a type of content-based filtering, which recommends items that are similar to the ones that the user has interacted with or selected, based on their attributes. For example, if a user selects a comedy movie from the US released in 2020, the system can recommend other comedy movies from the US released in 2020 or nearby years. This approach does not require any machine learning, but it can leverage the existing metadata of the videos to provide relevant recommendations. It also allows the system to start collecting user event data, such as views, likes, ratings, etc., which can be used to train a more sophisticated machine learning model in the future, such as a collaborative filtering model or a hybrid model that combines content and collaborative information. References:

Recommendation Systems

Content-Based Filtering

Collaborative Filtering

Hybrid Recommender Systems: A Systematic Literature Review

 The tf.data dataset is a TensorFlow API that provides a way to create and manipulate data pipelines for machine learning. The tf.data dataset allows you to apply various transformations to the data, such as reading, shuffling, batching, prefetching, and interleaving. These transformations can affect the performance and efficiency of the model training process1

One of the common performance issues in model training is input-bound, which means that the model is waiting for the input data to be ready and is not fully utilizing the computational resources. Input-bound can be caused by slow data loading, insufficient parallelism, or large data size. Input-bound can be detected by using the Cloud TPU profiler plugin, which is a tool that helps you analyze the performance of your model on Cloud TPUs. The Cloud TPU profiler plugin can show you the percentage of time that the TPU cores are idle, which indicates input-bound2

To reduce the input-bound bottleneck and speed up the model training process, you can make some modifications to the tf.data dataset. Two of the modifications that can help are:

Use the interleave option for reading data. The interleave option allows you to read data from multiple files in parallel and interleave their records. This can improve the data loading speed and reduce the idle time of the TPU cores. The interleave option can be applied by using the tf.data.Dataset.interleave method, which takes a function that returns a dataset for each input element, and a number of parallel calls3

Set the prefetch option equal to the training batch size. The prefetch option allows you to prefetch the next batch of data while the current batch is being processed by the model. This can reduce the latency between batches and improve the throughput of the model training. The prefetch option can be applied by using the tf.data.Dataset.prefetch method, which takes a buffer size argument. The buffer size should be equal to the training batch size, which is the number of examples per batch4

The other options are not effective or counterproductive. Reducing the value of the repeat parameter will reduce the number of epochs, which is the number of times the model sees the entire dataset. This can affect the model’s accuracy and convergence. Increasing the buffer size for the shuffle option will increase the randomness of the data, but also increase the memory usage and the data loading time. Decreasing the batch size argument in your transformation will reduce the number of examples per batch, which can affect the model’s stability and performance.

References: 1: tf.data: Build TensorFlow input pipelines 2: Cloud TPU Tools in TensorBoard 3: tf.data.Dataset.interleave 4: tf.data.Dataset.prefetch : [Better performance with the tf.data API]