MLS-C01 Practice Exam 52 — 20 Questions

Question 1

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. The most direct cause of an out-of-memory (OOM) error during GPU training is that the combined size of the model parameters, activations, and gradients exceeds the GPU's VRAM. Reducing the batch size immediately decreases the memory footprint of activations stored for backpropagation, which is the largest and most tunable memory consumer. This is the first and simplest step to resolve the error without altering the model architecture or training dynamics.

Answer

Add dropout layers

Answer

Use a smaller learning rate

Answer

Use gradient clipping

Question 2

A startup is deploying a machine learning model for real-time recommendation on Amazon SageMaker. The model is a TensorFlow model (1 GB) and the endpoint uses a single ml.c5.2xlarge instance. The inference latency is currently 500 ms per request. The startup expects traffic to increase 10x in the next month. They want to maintain latency under 500 ms. What is the most cost-effective solution?

Accepted Answer

Set up auto-scaling for the endpoint based on average latency or request count. Auto-scaling dynamically adds instances based on demand, handling a 10x increase in traffic while maintaining latency under 500 ms. This is more cost-effective than over-provisioning a larger instance (D) or switching to an expensive GPU instance (B). SageMaker Batch Transform (A) is not suitable for real-time inference.

Answer

Use SageMaker Batch Transform to process requests in batches

Answer

Switch to a GPU instance type for faster inference

Answer

Upgrade to a larger CPU instance type, such as ml.c5.4xlarge

Question 3

A company wants to use SageMaker to host multiple models behind a single endpoint to reduce costs. Which SageMaker feature should they use?

Accepted Answer

SageMaker Multi-Model Endpoints. SageMaker Multi-Model Endpoints allow you to deploy multiple models behind a single endpoint, each loaded dynamically from Amazon S3 based on the inference request. This reduces hosting costs by sharing a single instance across many models, as only the models that are actively invoked consume memory. The correct answer is E because this feature is specifically designed for cost-efficient multi-model hosting.

Answer

SageMaker Elastic Inference

Answer

SageMaker inference pipeline

Answer

SageMaker batch transform

Answer

SageMaker multi-container endpoints

Question 4

A data scientist runs a SageMaker training job that fails with the above error. The S3 bucket and object exist, and the IAM role has s3:GetObject permission. What is the MOST likely cause?

Accepted Answer

The S3 object was uploaded with incorrect checksum or is corrupted. The error indicates that SageMaker cannot read the S3 object, even though the bucket and object exist and the IAM role has s3:GetObject permission. The most likely cause is that the object was uploaded with an incorrect checksum or is corrupted, which prevents SageMaker from verifying the integrity of the data during the training job initialization. SageMaker uses ETag (MD5 checksum) validation when reading objects, and a mismatch triggers a failure.

Answer

The training instance does not have internet access

Answer

The S3 bucket has versioning enabled and the object version is not specified

Answer

The IAM role lacks kms:Decrypt permission for an encrypted S3 object

Question 5

A machine learning engineer is building a pipeline to preprocess data and train a model using Amazon SageMaker. The data is stored in Amazon S3 and the preprocessing step is computationally intensive. The engineer wants to minimize costs while ensuring that the preprocessing step does not fail due to instance termination. Which instance type should be used for the preprocessing step?

Accepted Answer

On-demand instances. On-demand instances (Option B) are the correct choice because they provide reliable, non-interruptible compute capacity for the preprocessing step. Spot instances can be terminated at any time (with a 2-minute warning) when AWS reclaims capacity, which would cause the computationally intensive preprocessing to fail. Reserved instances require a 1- or 3-year commitment and are not cost-effective for a single preprocessing job that may not run continuously.

Answer

Reserved instances

Answer

A larger instance type to speed up processing

Answer

Spot instances

Question 6

A company needs to ingest real-time clickstream data from thousands of web servers into AWS for near-real-time analytics. The data volume varies and can spike during promotions. Which service should be used to capture and buffer the data before processing?

Accepted Answer

Amazon Kinesis Data Streams. Amazon Kinesis Data Streams is the correct choice because it is designed for real-time data ingestion and buffering of large streams of data, such as clickstream events from thousands of web servers. It provides durable, low-latency storage (up to 365 days retention) and supports multiple consumers for near-real-time analytics, making it ideal for handling variable and spiky data volumes during promotions.

Answer

Amazon SQS

Answer

Amazon Kinesis Data Firehose

Answer

Amazon MQ

Question 7

A company wants to use Amazon SageMaker to train a model using a custom algorithm packaged in a Docker container. Which approach should they use?

Accepted Answer

Use the SageMaker SDK to create an Estimator with the image URI of the custom container. The correct approach is to use the SageMaker SDK to create an Estimator with the image URI of the custom container, as SageMaker supports bring-your-own-container for custom algorithms. Option A is incorrect because SageMaker Ground Truth is a labeling service, not for training custom algorithms. Option B is incorrect because SageMaker Autopilot automates model selection and tuning, but it does not support custom containers. Option D is incorrect because built-in algorithms are predefined and do not allow custom code.

Answer

Use SageMaker Ground Truth

Answer

Use SageMaker Autopilot

Answer

Select one of the built-in algorithms in SageMaker

Question 8

A machine learning team is building a model to predict customer churn. They have a dataset with 10,000 samples and 50 features, including categorical variables with high cardinality (e.g., ZIP code). Which feature engineering technique is most appropriate to reduce dimensionality while preserving predictive information?

Accepted Answer

Target encoding. Target encoding replaces high-cardinality categories with the mean target value, reducing dimensionality while capturing predictive signal. Option A (PCA) is wrong because PCA is applied to numerical features, not categorical. Option B (One-hot encoding) is wrong because one-hot encoding creates many sparse features, increasing dimensionality. Option D is wrong because label encoding imposes ordinality that may not exist.

Answer

Principal Component Analysis (PCA)

Answer

One-hot encoding

Answer

Label encoding

Question 9

A company wants to deploy a machine learning model that performs real-time inference with sub-second latency. The model is a deep neural network with 500 MB of weights. The inference endpoint must scale to zero when not in use to minimize cost. Which AWS service should the company use?

Accepted Answer

Use Amazon SageMaker Serverless Inference to host the model.. Amazon SageMaker Serverless Inference is designed for workloads with intermittent traffic patterns, automatically scaling to zero when idle and scaling up for real-time requests. It supports models up to 1 GB in size and provides sub-second latency for inference, making it ideal for this 500 MB deep neural network. This service eliminates the need to manage underlying infrastructure while meeting the latency and cost requirements.

Answer

Deploy the model as an AWS Lambda function with provisioned concurrency.

Answer

Host the model on Amazon ECS with Fargate and use a target tracking scaling policy.

Answer

Create an Amazon SageMaker real-time endpoint with automatic scaling policies.

Question 10

A data engineer needs to schedule an AWS Glue ETL job to run every hour. Which service should be used to trigger the job?

Accepted Answer

Amazon CloudWatch Events (EventBridge). Amazon CloudWatch Events (now part of Amazon EventBridge) is the correct service for scheduling AWS Glue ETL jobs on a recurring basis, such as every hour. It allows you to create a time-based rule using a cron or rate expression that triggers an AWS Glue job directly as a target, without needing additional compute or orchestration logic.

Answer

AWS Lambda

Answer

AWS Step Functions

Answer

AWS Data Pipeline

Question 11

A data scientist is training a linear regression model to predict house prices. The dataset contains 10 features. After training, the data scientist notices that the model has high bias (underfitting). Which action should the data scientist take to reduce bias?

Accepted Answer

Add more features, such as polynomial features. High bias (underfitting) means the model is too simple to capture the underlying patterns in the data. Adding more features, such as polynomial features, increases model complexity, allowing the linear regression model to fit non-linear relationships and reduce bias. This directly addresses the underfitting issue by giving the model more expressive power.

Answer

Reduce the amount of training data

Answer

Increase the regularization strength

Answer

Use a simpler model, such as ridge regression

Question 12

A company uses Amazon Redshift as a data warehouse. They need to load 50 TB of clickstream data from S3 into Redshift daily. The data arrives in 5-minute intervals as gzipped CSV files. The target table has a sort key and a distribution key. The load must complete within 2 hours. Which approach is MOST efficient?

Accepted Answer

Use the COPY command with a manifest file and gzip compression.. The COPY command is the most efficient way to load large volumes of data into Amazon Redshift because it uses the cluster's massively parallel processing (MPP) architecture to read data directly from S3 in parallel across all nodes. With a manifest file, you can specify multiple gzipped CSV files, and the gzip compression reduces network I/O and storage overhead. This approach can easily load 50 TB within 2 hours, especially when the target table has a sort key and distribution key, as COPY automatically leverages these for optimal data distribution and sorting during the load.

Answer

Use AWS Glue to transform the data and write to Redshift using JDBC.

Answer

Use a staging table and then merge using a stored procedure.

Answer

Use a series of INSERT statements from a Lambda function.

Question 13

A company is building a real-time anomaly detection system for network traffic logs. The logs are ingested via Amazon Kinesis Data Streams and processed with an Amazon SageMaker endpoint for inference. The team needs to ensure that the inference results are stored durably and can be replayed for model retraining. The system must handle at least 10,000 records per second with low latency. Which three AWS services should the team use to build this architecture? (Select THREE.)

Accepted Answer

Amazon Kinesis Data Streams. Amazon Kinesis Data Streams is the correct ingestion layer because it provides durable, real-time data streaming with the ability to handle over 10,000 records per second. It acts as the source of truth for network traffic logs, enabling low-latency processing and replay for model retraining.

Answer

AWS Glue ETL

Answer

Amazon Kinesis Data Firehose

Question 14

A data pipeline uses AWS Glue to transform data from Amazon RDS to Amazon S3. The team wants to ensure that only new or updated records are processed in each run, minimizing cost and time. Which AWS Glue feature should be used?

Accepted Answer

Enable Glue Job Bookmarks.. Glue Job Bookmarks track processed data and persist state between job runs, enabling incremental processing of new or updated records from a source like Amazon RDS. This minimizes cost and time by avoiding full table scans and reprocessing unchanged data.

Answer

Use Glue triggers to run the job on a schedule.

Answer

Use Glue partition pruning to filter data.

Answer

Use Glue crawlers to detect new data.

Question 15

Which TWO metrics are MOST appropriate for evaluating a regression model that predicts house prices, where the business is most sensitive to large errors?

Accepted Answer

Root Mean Squared Error (RMSE). RMSE is most appropriate because it squares the errors before averaging, which heavily penalizes large errors. Since the business is most sensitive to large errors in house price predictions, RMSE directly aligns with this requirement by amplifying the impact of outliers, making it a suitable metric for evaluating model performance in this context.

Answer

Accuracy

Answer

Mean Absolute Error (MAE)

Answer

R-squared

Question 16

A data scientist is training a recurrent neural network (RNN) for time series forecasting. The training loss decreases steadily for the first 10 epochs, then plateaus. The validation loss starts increasing after epoch 10. What is the most appropriate action?

Accepted Answer

Stop training early and use the model from epoch 10. The validation loss increasing while training loss decreases indicates overfitting. Early stopping halts training before overfitting worsens, preserving the model that performed best on validation data (epoch 10). Option B (continuing training) would increase overfitting. Option C (adding layers) may exacerbate overfitting. Option D (increasing batch size) is not directly addressing overfitting and may not help.

Answer

Continue training for more epochs

Answer

Add more layers to the network

Answer

Increase the batch size

Question 17

Which TWO of the following are valid techniques to handle missing data in a dataset?

Accepted Answer

Mean imputation. Mean imputation (Option C) is a valid technique for handling missing data because it replaces missing values with the mean of the observed values for that feature, preserving the overall mean of the dataset. This approach is simple and effective for numerical data that is missing completely at random (MCAR), as it does not introduce bias in the mean estimate.

Answer

Normalizing the data

Answer

Adding a constant value of 0

Answer

Synthetic Minority Over-sampling (SMOTE)

Question 18

A data scientist needs to run a one-time training job on a 5 TB dataset stored in Amazon S3. The training algorithm requires random access to individual records. Which SageMaker input mode and data format combination would be MOST appropriate?

Accepted Answer

Use File mode with RecordIO-Protobuf format. File mode loads the entire 5 TB dataset onto the SageMaker instance's local SSD, providing low-latency random access to individual records, which is required by the training algorithm. RecordIO-Protobuf format is optimized for SageMaker's internal data pipeline, enabling efficient deserialization and batching during training. This combination ensures the algorithm can randomly access any record without the sequential streaming constraints of Pipe mode.

Answer

Use Pipe mode with Parquet format

Answer

Use Pipe mode with RecordIO-Protobuf format

Answer

Use Pipe mode with CSV format

Question 19

Refer to the exhibit. An IAM policy is attached to a SageMaker notebook instance. The data scientist runs a training job that reads from s3://my-bucket/training-data/ and writes to s3://my-bucket/output/. The training job fails with an access denied error. What is the most likely cause?

Accepted Answer

The policy does not allow s3:PutObject on the output location. The training job fails because the IAM policy does not grant s3:PutObject permission to the output location (s3://my-bucket/output/). The policy likely only allows s3:PutObject on the training-data prefix. Option A is incorrect because sagemaker:CreateTrainingJob is not directly related to write access; the job can be created but execution fails. Option C is incorrect because InvokeEndpoint is used for real-time inference, not training. Option D is incorrect because the policy does allow s3:GetObject on the training data (as it permits read access to that prefix).

Answer

The policy does not allow sagemaker:CreateTrainingJob

Answer

The policy is missing the sagemaker:InvokeEndpoint action

Answer

The policy does not allow s3:GetObject on the training data

Question 20

Refer to the exhibit. An IAM policy is attached to an IAM role used by a SageMaker training job. The training job fails with an access denied error when trying to write model artifacts to an S3 bucket. What is the most likely cause?

Accepted Answer

The IAM role does not have permission to write to the S3 bucket. The IAM role attached to the SageMaker training job must have an IAM policy that grants s3:PutObject permission on the S3 bucket where model artifacts are written. The access denied error indicates that the role lacks the necessary write permissions for that specific bucket, causing the training job to fail when it attempts to upload the model output.

Answer

The training job is trying to write to a different S3 bucket

Answer

The IAM role does not have permission to read the training data

Answer

The IAM role does not have permission to create training jobs