MLS-C01 Machine Learning Implementation and Operations Practice Test 4 — 15 Questions

Question 1

A machine learning pipeline uses SageMaker Processing jobs for feature engineering. Which TWO are benefits of using SageMaker Processing over running a custom script on an EC2 instance?

Accepted Answer

Automatically manages the compute resources. Options B and D are correct. Option B: SageMaker Processing manages infrastructure. Option D: Integrates with SageMaker experiments. Option A is wrong because EC2 can also use various runtimes. Option C is wrong because EC2 instance can be in a VPC. Option E is wrong because both can use Git.

Answer

Provides a built-in VPC for network isolation

Answer

Allows use of custom Docker images from any registry

Answer

Supports multiple programming languages

Question 2

Refer to the exhibit. A data scientist runs the AWS CLI command to create a SageMaker training job. The training job fails because the input data is not accessible. Which step should the data scientist take to fix the issue?

Accepted Answer

Attach an IAM policy to SageMakerRole that grants s3:GetObject on the bucket. Option B is correct because the IAM role must have s3:GetObject permission for the S3 bucket. Option A is wrong because the bucket policy is separate. Option C is wrong because VolumeSizeInGB is for local storage, not S3. Option D is wrong because VPC configuration is not the issue.

Answer

Add a VpcConfig to the training job

Answer

Modify the bucket policy to allow s3:GetObject for any principal

Answer

Increase VolumeSizeInGB to 50

Question 3

Refer to the exhibit. A SageMaker training job uses an IAM role with this policy. The training job writes output to s3://my-bucket/output/. Which statement about the policy is true?

Accepted Answer

The training job can write output objects only if server-side encryption with SSE-S3 is used. Option C is correct because the Deny statement blocks PutObject without SSE-S3 (AES256). Option A is wrong because Deny with condition allows PutObject when condition is met. Option B is wrong because Deny overrides Allow. Option D is wrong because GetObject is allowed without encryption requirement.

Answer

The Allow statement allows all PutObject requests regardless of encryption

Answer

The Deny statement blocks all PutObject requests

Answer

The GetObject permission requires the object to be encrypted with SSE-S3

Question 4

Refer to the exhibit. A SageMaker endpoint is returning 5xx errors. The logs show the above error. Which change will most likely resolve the issue?

Accepted Answer

Use a larger instance type with more memory. Option B is correct because increasing memory (e.g., upgrading instance type) addresses the OutOfMemoryError. Option A is wrong because batch size is not relevant for inference (single request). Option C is wrong because the error is memory, not model file size. Option D is wrong because AutoScaling does not change instance memory.

Answer

Reduce the batch size in the inference script

Answer

Enable Auto Scaling on the endpoint

Answer

Compress the model artifact

Question 5

A team is using SageMaker to train a model using the built-in XGBoost algorithm. The training job is taking longer than expected. The team suspects that the data is not being loaded efficiently. Which data format should they use to minimize training time?

Accepted Answer

Pipe mode with RecordIO-Protobuf. Option B is correct because Pipe mode streams data from S3 directly to the algorithm, reducing initialization time. Option A is wrong because File mode downloads data first. Option C is wrong because CSV is not as efficient as RecordIO for XGBoost. Option D is wrong because Parquet is not natively supported by XGBoost in SageMaker.

Answer

Pipe mode with CSV

Answer

File mode with Parquet

Answer

File mode with CSV

Question 6

A company uses SageMaker Ground Truth to label images for object detection. After labeling, they notice that the bounding boxes are often misaligned with the objects. Which action should they take to improve label quality?

Accepted Answer

Use a pre-built annotation tool that enforces bounding box alignment. Option C is correct because using a pre-built annotation tool reduces variability. Option A is wrong because increasing workers does not guarantee consistency. Option B is wrong because automated labeling may not be accurate initially. Option D is wrong because adjusting confidence threshold is for post-processing, not labeling.

Answer

Use automated labeling with a pre-trained model

Answer

Increase the number of workers per task

Answer

Adjust the confidence threshold for the model

Question 7

A data scientist needs to create a SageMaker notebook instance with access to a private S3 bucket. The bucket uses SSE-KMS encryption. Which additional configuration is required?

Accepted Answer

Attach a policy to the notebook's IAM role that allows kms:Decrypt. Option D is correct because the notebook instance needs permission to use the KMS key. Option A is wrong because VPC is optional. Option B is wrong because lifecycle configuration does not handle encryption. Option C is wrong because bucket policy is separate.

Answer

Add a lifecycle configuration script

Answer

Modify the bucket policy to allow s3:GetObject

Answer

Place the notebook instance in a VPC

Question 8

You are building a CI/CD pipeline for SageMaker using AWS CodePipeline. Which THREE components are essential for a fully automated model training and deployment pipeline?

Accepted Answer

AWS CodeCommit to store the training script and model code. Options A, B, and D are correct. Option A: CodeCommit stores code. Option B: CodeBuild can run training jobs. Option D: Lambda can trigger SageMaker endpoints. Option C is wrong because CodeDeploy is for EC2, not SageMaker. Option E is wrong because CloudFormation is optional.

Answer

AWS CodeDeploy to deploy the model to an endpoint

Answer

AWS CloudFormation to define the infrastructure

Question 9

A company uses SageMaker to run training jobs on a schedule. The training data is stored in an S3 bucket that receives new data every hour. Which TWO approaches can the company use to trigger a training job when new data arrives?

Accepted Answer

Set up an Amazon EventBridge rule that triggers on S3 Object Created events and targets a Lambda function. Options B and D are correct. Option B: S3 events can invoke Lambda to start training. Option D: EventBridge rule can trigger on custom events. Option A is wrong because CloudWatch Logs are for logs, not events. Option C is wrong because SQS is not directly integrated with SageMaker. Option E is wrong because Step Functions would need a trigger.

Answer

Use an SQS queue to buffer S3 events and poll from a training instance

Answer

Use AWS Step Functions with a scheduled execution

Answer

Use CloudWatch Logs to monitor S3 access logs and trigger a Lambda function

Question 10

You are deploying a PyTorch model to a SageMaker endpoint. The model is large (5 GB) and the endpoint is using an ml.c5.2xlarge instance. Inference latency is higher than required. Which change would most effectively reduce latency?

Accepted Answer

Use a GPU instance type such as ml.p3.2xlarge. Option D is correct because using a GPU instance accelerates PyTorch inference. Option A is wrong because Elastic Inference could help but may not be as effective as full GPU. Option B is wrong because smaller batch size may increase latency per request. Option C is wrong because reducing workers can increase latency.

Answer

Reduce the batch size in the inference code

Answer

Decrease the number of model server workers

Answer

Enable SageMaker Elastic Inference

Question 11

A data scientist needs to deploy a PyTorch model for real-time inference. Which AWS service is best suited for this task?

Accepted Answer

Amazon SageMaker real-time endpoint. Option D is correct because Amazon SageMaker provides built-in support for deploying PyTorch models with real-time endpoints. Option A is wrong because AWS Lambda has limited memory and runtime duration. Option B is wrong because SageMaker Batch Transform is for offline inference. Option C is wrong because ECS requires manual setup for model serving.

Answer

Amazon SageMaker Batch Transform

Answer

Amazon ECS with Fargate

Answer

AWS Lambda with custom container

Question 12

A company uses SageMaker to train a model, but the training job fails due to insufficient memory. What is the most cost-effective way to resolve this?

Accepted Answer

Use a larger instance type with more memory. Option A is correct because increasing instance memory addresses the issue directly. Option B is wrong because reducing batch size may not solve memory issues if the model itself is large. Option C is wrong because Spot Instances have no memory advantage. Option D is wrong because distributed training adds complexity and cost.

Answer

Use Spot Instances to reduce cost

Answer

Reduce the batch size in the training script

Answer

Switch to distributed training across multiple instances

Question 13

A team wants to automate the retraining of a model weekly using new data that arrives in S3. Which combination of services should they use?

Accepted Answer

Amazon SageMaker Pipelines and S3 events. Option C is correct because SageMaker Pipelines provides a managed workflow for training and retraining. Option A is wrong because Step Functions alone is not ML-specific. Option B is wrong because Lambda is not designed for long-running training. Option D is wrong because SageMaker Processing is for data processing, not full pipeline automation.

Answer

AWS Lambda and S3 events

Answer

Amazon SageMaker Processing jobs

Answer

AWS Step Functions and AWS Glue

Question 14

A deployed SageMaker endpoint is returning high latency. The model is a scikit-learn Random Forest. Which action is most likely to reduce latency?

Accepted Answer

Reduce the number of trees in the ensemble. Option D is correct because reducing the number of trees directly speeds up inference. Option A is wrong because increasing instance count may not reduce per-request latency. Option B is wrong because using GPU may not help tree-based models. Option C is wrong because pruning reduces accuracy but is not the best approach.

Answer

Prune decision trees in the model

Answer

Increase the number of instances behind the endpoint

Answer

Switch to a GPU instance type

Question 15

A data scientist needs to run a hyperparameter tuning job for a deep learning model. Which SageMaker feature should they use?

Accepted Answer

SageMaker Hyperparameter Tuning Job. Option B is correct because SageMaker Hyperparameter Tuning Jobs are designed for this purpose. Option A is wrong because Automatic Model Tuning is the same as hyperparameter tuning but the correct term is 'Hyperparameter Tuning Job'. Option C is wrong because SageMaker Experiments track runs, not tune. Option D is wrong because SageMaker Processing is for data processing.

Answer

SageMaker Experiments

Answer

SageMaker Automatic Model Tuning

Answer

SageMaker Processing