Free Access to Google.Professional-Machine-Learning-Engineer.v2024-01-19.q113 with Valid Practice Test (Page 23)

Question 106

You are an ML engineer at a global shoe store. You manage the ML models for the company's website. You are asked to build a model that will recommend new products to the user based on their purchase behavior and similarity with other users. What should you do?

A.Build a classification model
B.Build a knowledge-based filtering model
C.Build a regression model using the features as predictors
D.Build a collaborative-based filtering model

Question 107

You need to train a regression model based on a dataset containing 50,000 records that is stored in BigQuery. The data includes a total of 20 categorical and numerical features with a target variable that can include negative values. You need to minimize effort and training time while maximizing model performance. What approach should you take to train this regression model?

A.Create a custom TensorFlow DNN model.
B.Use BQML XGBoost regression to train the model
C.Use AutoML Tables to train the model without early stopping.
D.Use AutoML Tables to train the model with RMSLE as the optimization objective

Question 108

You are creating a deep neural network classification model using a dataset with categorical input values.
Certain columns have a cardinality greater than 10,000 unique values. How should you encode these categorical values as input into the model?

A.Convert each categorical value into an integer value.
B.Convert the categorical string data to one-hot hash buckets.
C.Map the categorical variables into a vector of boolean values.
D.Convert each categorical value into a run-length encoded string.

Question 109

You are designing an architecture with a serveress ML system to enrich customer support tickets with informative metadata before they are routed to a support agent. You need a set of models to predict ticket priority, predict ticket resolution time, and perform sentiment analysis to help agents make strategic decisions when they process support requests. Tickets are not expected to have any domain-specific terms or jargon.
The proposed architecture has the following flow:

Which endpoints should the Enrichment Cloud Functions call?

A.1 = Al Platform, 2 = Al Platform, 3 = AutoML Vision
B.1 = Al Platform, 2 = Al Platform, 3 = AutoML Natural Language
C.1 = Al Platform, 2 = Al Platform, 3 = Cloud Natural Language API
D.1 = cloud Natural Language API, 2 = Al Platform, 3 = Cloud Vision API

Question 110

You manage a team of data scientists who use a cloud-based backend system to submit training jobs. This system has become very difficult to administer, and you want to use a managed service instead. The data scientists you work with use many different frameworks, including Keras, PyTorch, theano, scikit-learn, and custom libraries. What should you do?

A.Use the Vertex AI Training to submit training jobs using any framework.
B.Configure Kubeflow to run on Google Kubernetes Engine and submit training jobs through TFJob.
C.Create a library of VM images on Compute Engine, and publish these images on a centralized repository.
D.Set up Slurm workload manager to receive jobs that can be scheduled to run on your cloud infrastructure.

Correct Answer: A

The best option for using a managed service to submit training jobs with different frameworks is to use Vertex AI Training. Vertex AI Training is a fully managed service that allows you to train custom models on Google Cloud using any framework, such as TensorFlow, PyTorch, scikit-learn, XGBoost, etc. You can also use custom containers to run your own libraries and dependencies. Vertex AI Training handles the infrastructure provisioning, scaling, and monitoring for you, so you can focus on your model development and optimization.
Vertex AI Training also integrates with other Vertex AI services, such as Vertex AI Pipelines, Vertex AI Experiments, and Vertex AI Prediction. The other options are not as suitable for using a managed service to submit training jobs with different frameworks, because:
* Configuring Kubeflow to run on Google Kubernetes Engine and submit training jobs through TFJob would require more infrastructure maintenance, as Kubeflow 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 training job usage. TFJob is also mainly designed for TensorFlow models, and might not support other frameworks as well as Vertex AI Training.
* Creating a library of VM images on Compute Engine, and publishing these images on a centralized repository would require more development time and effort, as you would have to create and maintain different VM images for different frameworks and libraries. You would also have to manually configure and launch the VMs for each training job, and handle the scaling and monitoring yourself. This would not leverage the benefits of a managed service, such as Vertex AI Training.
* Setting up Slurm workload manager to receive jobs that can be scheduled to run on your cloud infrastructure would require more configuration and administration, as Slurm is not a native Google Cloud service, and you would have to install and manage it on your own VMs or clusters. Slurm is also a general-purpose workload manager, and might not have the same level of integration and optimization for ML frameworks and libraries as Vertex AI Training. References:
* Vertex AI Training | Google Cloud
* Kubeflow on Google Cloud | Google Cloud
* TFJob for training TensorFlow models with Kubernetes | Kubeflow
* Compute Engine | Google Cloud
* Slurm Workload Manager

Question 106

Question 107

Question 108

Question 109

Question 110

Download PDF File