MLS-C01 Machine Learning Implementation and Operations Practice Test 3 — 15 Questions

Question 1

A company uses Amazon SageMaker to train a text classification model. The training data is stored in S3 and contains sensitive personally identifiable information (PII). The company must ensure that the data is encrypted at rest in S3 and that the encryption key is managed by the company's own hardware security module (HSM). Which configuration should be used?

Accepted Answer

Use S3 server-side encryption with customer-provided keys (SSE-C) and store the keys in the HSM. Option A is correct because SSE-C allows customers to provide their own encryption keys, which can be stored in an HSM. Option B (SSE-S3) uses AWS-managed keys. Option C (SSE-KMS with a customer managed key) uses KMS, not HSM. Option D (client-side encryption) requires managing encryption in the application.

Answer

Use S3 server-side encryption with S3-managed keys (SSE-S3)

Answer

Use client-side encryption with the encryption key stored in the HSM

Answer

Use S3 server-side encryption with AWS KMS managed keys (SSE-KMS) with a customer managed key

Question 2

A data scientist is using Amazon SageMaker to train an XGBoost model on a dataset with missing values. The dataset has both numeric and categorical features. Which preprocessing step is MOST appropriate before training?

Accepted Answer

One-hot encode categorical features and let XGBoost handle missing values natively. Option D is correct because XGBoost can handle missing values natively, so imputation may not be necessary, and one-hot encoding is needed for categorical features. Option A (mean imputation) may be okay but not necessary. Option B (remove rows) loses data. Option C (label encoding) may create ordinal relationships.

Answer

Impute missing numeric values with the mean and categorical values with the mode, then train without encoding

Answer

Remove all rows with missing values and train on the remaining data

Answer

Label encode categorical features and use the built-in missing value handling of XGBoost

Question 3

An ML team is using Amazon SageMaker to train a model. They notice that the training job is taking longer than expected and the CloudWatch metrics show high GPU utilization but low CPU utilization. Which action is MOST likely to improve training speed?

Accepted Answer

Use SageMaker Pipe mode to stream data from S3 to reduce I/O bottleneck. Option B is correct because high GPU utilization indicates the GPU is busy, but low CPU may indicate a bottleneck in data loading; using Pipe mode can reduce I/O wait. Option A (increase instance count) may help if the job is parallelizable but not if the bottleneck is data loading. Option C (increase GPU memory) does not address data loading. Option D (use CPU instance) would slow down training.

Answer

Switch to a CPU-only instance to avoid GPU overhead

Answer

Increase the number of training instances

Answer

Use a larger GPU instance with more GPU memory

Question 4

A company is using Amazon SageMaker to host a model that performs real-time inference. The model receives around 100 requests per second with occasional spikes up to 500 requests per second. The current endpoint uses 2 ml.m5.large instances. During spikes, latency increases significantly, and some requests time out. What is the MOST cost-effective solution to handle the spikes without losing requests?

Accepted Answer

Configure SageMaker managed scaling with a target tracking policy and add a buffer based on the average spike duration. Option C is correct because adding a buffer to the autoscaling policy allows the endpoint to scale proactively before the spike fully hits, while managed scaling adjusts instances based on demand. Option A (increase instance size) is less cost-effective than scaling out. Option B (SQS) adds latency. Option D (Lambda) may not be suitable for real-time inference.

Answer

Replace the instances with a single larger instance type, such as ml.m5.4xlarge

Answer

Use an Amazon SQS queue to buffer incoming requests and process them asynchronously

Answer

Use AWS Lambda with a provisioned concurrency to handle the spikes

Question 5

Which TWO configuration steps are necessary to deploy a custom Docker container for training in Amazon SageMaker? (Choose two.)

Accepted Answer

Implement the train function in the container that saves model artifacts to /opt/ml/model. Options B and D are correct. SageMaker requires the container to have a training script at /opt/ml/code and to implement the train function. Option A is incorrect because the container must be stored in ECR, not Docker Hub. Option C is optional. Option E is incorrect because SageMaker does not use Docker Compose.

Answer

Expose a REST API endpoint for inference

Answer

Define a Docker Compose file to manage multi-container training

Answer

Push the container image to Docker Hub

Question 6

Which THREE actions can help reduce the inference latency of a SageMaker endpoint? (Choose three.)

Accepted Answer

Use a larger instance type with more CPU/GPU. Options A, B, and E are correct. Using a larger instance with more compute power, enabling SageMaker Batch Transform for offline predictions, and enabling data compression reduce latency. Option C (multi-model endpoint) helps with memory but not latency. Option D (more instances) improves throughput but not per-request latency.

Answer

Use a multi-model endpoint to share instances across models

Answer

Increase the number of instances in the endpoint

Question 7

Which TWO services can be used to perform hyperparameter tuning in Amazon SageMaker? (Choose two.)

Accepted Answer

Amazon SageMaker Automatic Model Tuning. Options A and B are correct. SageMaker Automatic Model Tuning is the native tuning service. SageMaker Experiments can track tuning jobs. Option C (SageMaker Ground Truth) is for labeling. Option D (AWS Glue) is for ETL. Option E (Amazon EMR) is for big data processing.

Answer

AWS Glue

Answer

Amazon SageMaker Ground Truth

Answer

Amazon EMR

Question 8

An IAM policy is attached to a SageMaker notebook instance. The data scientist wants to use the notebook to train a model using data from S3 bucket 'my-bucket'. However, the training job fails with an access denied error. What is the MOST likely cause?

Accepted Answer

The notebook instance role does not have iam:PassRole permission to pass the SageMaker execution role. Option B is correct because the notebook instance role needs permission to pass the execution role to SageMaker (iam:PassRole). The policy allows s3 and sagemaker actions but not PassRole. Option A is incorrect because GetObject and PutObject are allowed. Option C is incorrect because SageMaker actions are allowed. Option D is incorrect because the resource is correct.

Answer

The sagemaker:CreateTrainingJob permission is not allowed on the specific resource

Answer

The S3 bucket resource ARN is incorrectly formatted

Answer

The s3:GetObject permission is missing for the bucket

Question 9

A SageMaker endpoint creation fails with the above CloudWatch Logs excerpt. What is the MOST likely cause?

Accepted Answer

The model file is too large and takes longer than 300 seconds to load. Option C is correct because the model file may be too large to load within the default timeout. Option A (missing inference script) would cause a different error. Option B (incorrect S3 permissions) would appear earlier. Option D (instance type) would cause resource issues but not a timeout on loading.

Answer

The S3 bucket containing the model artifacts has incorrect permissions

Answer

The inference script has a syntax error

Answer

The instance type does not have enough memory to load the model

Question 10

A data scientist runs the AWS CLI command shown in the exhibit. The output shows that job-2 failed. Which action should the data scientist take to diagnose the failure?

Accepted Answer

Run `aws sagemaker describe-training-job --training-job-name job-2` to see the failure reason. Option A is correct because the DescribeTrainingJob API provides detailed status and failure reason. Option B (list-training-jobs) already used. Option C (CloudWatch Logs) is useful but the first step is to get the failure reason from DescribeTrainingJob. Option D (S3 logs) is not standard.

Answer

Check the CloudWatch Logs log group for job-2

Answer

Check the S3 bucket for any error logs uploaded by the training job

Answer

Run `aws sagemaker list-training-jobs --name-contains job-2` to get more details

Question 11

A data science team is deploying a machine learning model to production using Amazon SageMaker. The model requires real-time inference with low latency. Which SageMaker feature should they use to deploy the model?

Accepted Answer

SageMaker Realtime Endpoint. Option C is correct because SageMaker Realtime Endpoints provide low-latency, synchronous inference. Option A is wrong because batch transform is for asynchronous, batch predictions. Option B is wrong because SageMaker Notebooks are for development, not deployment. Option D is wrong because SageMaker Autopilot automates model building, not deployment.

Answer

SageMaker Notebook Instance

Answer

SageMaker Batch Transform

Answer

SageMaker Autopilot

Question 12

During training of a deep learning model on a GPU instance in SageMaker, the training job fails with an insufficient memory error. Which step should be taken first to resolve this issue?

Accepted Answer

Reduce the batch size. Option B is correct because reducing the batch size directly decreases GPU memory usage. Option A is wrong because it reduces training time but not memory per step. Option C is wrong because it addresses vanishing gradients, not memory. Option D is wrong because it reduces overfitting, not memory.

Answer

Add dropout layers

Answer

Use a smaller learning rate

Answer

Use gradient clipping

Question 13

A company uses SageMaker to train a model each night. The training data is stored in an S3 bucket with SSE-S3 encryption. The training job fails with an access denied error. Which configuration is needed?

Accepted Answer

Create an IAM role with S3 read access and assign it to the SageMaker training job. Option C is correct because SageMaker needs an IAM role with S3 permissions and the role must be passed to the training job. Option A is wrong because KMS is not used with SSE-S3. Option B is wrong because bucket policy alone is insufficient without the SageMaker role. Option D is wrong because VPC is not related to encryption.

Answer

Configure the training job to run in a VPC with S3 VPC Endpoint

Answer

Enable SSE-KMS on the S3 bucket

Answer

Add a bucket policy allowing s3:GetObject for all principals

Question 14

A data scientist is deploying a model to a SageMaker endpoint and needs to optimize for cost while maintaining low latency. Which TWO actions should the data scientist take?

Accepted Answer

Use SageMaker Serverless Inference. Options A and D are correct. Option A: Serverless Inference automatically scales and costs are based on usage. Option D: Auto Scaling adjusts instance count based on traffic, reducing cost during low demand. Option B is wrong because larger instances increase cost. Option C is wrong because batch transform is not real-time. Option E is wrong because reducing instances increases latency.

Answer

Use a larger instance type

Answer

Deploy to a single instance

Answer

Switch to batch transform

Question 15

You are deploying a custom Docker container for a SageMaker model that requires a specific NVIDIA CUDA version. Which THREE steps must you take to ensure the container runs correctly on SageMaker?

Accepted Answer

Include the SageMaker inference toolkit in the container. Options A, B, and D are correct. Option A: Container must support the SageMaker inference toolkit. Option B: Must set the correct entry point. Option D: Must run on a GPU instance. Option C is wrong because batch transform is not required. Option E is wrong because health check is recommended but not mandatory.

Answer

Define a health check endpoint

Answer

Use SageMaker Batch Transform