Practice Mode

MLA-C01

Loading...

MLA-C01 — 20 free practice questions

Preview the exam for free. Unlock all 240 questions →

Question 1

Which action will meet this requirement with the LEAST operational overhead?
  • A. Create a separate Amazon Elastic Container Registry (Amazon ECR) repository for each model.
  • B. Use Amazon Elastic Container Registry (Amazon ECR) and unique tags for each model version.
  • C. Use the SageMaker Model Registry and model groups to catalog the models. Correct
  • D. Use the SageMaker Model Registry and unique tags for each model version.

Explanation

The correct answer is C because Amazon SageMaker's Model Registry provides a built-in feature to manage different versions of machine learning models within model groups, which aligns with the requirement for a central model registry. This approach reduces operational overhead compared to using separate repositories or tags in Amazon ECR.

Question 2

How can the company MINIMIZE infrastructure startup times for these jobs? Options: A. Use Managed Spot Training. B. Use SageMaker managed warm pools. C. Use SageMaker Training Compiler. D. Use the SageMaker distributed data parallelism (SMDDP) library.
  • A. Use Managed Spot Training.
  • B. Use SageMaker managed warm pools. Correct
  • C. Use SageMaker Training Compiler.
  • D. Use the SageMaker distributed data parallelism (SMDDP) library.

Explanation

SageMaker managed warm pools minimize infrastructure startup times for consecutive training jobs by keeping instances ready and available, thus reducing the time needed to provision resources when starting new jobs. This approach ensures that the next job can start quickly without waiting for instance provisioning.

Question 3

Which solution will meet this requirement?
  • A. Use SageMaker Experiments to facilitate the approval process during model registration.
  • B. Use SageMaker ML Lineage Tracking on the central model registry. Create tracking entities for the approval process.
  • C. Use SageMaker Model Monitor to evaluate the performance of the model and to manage the approval.
  • D. Use SageMaker Pipelines. When a model version is registered, use the AWS SDK to change the approval status to "Approved." Correct

Explanation

SageMaker Pipelines support manual approval steps in the workflow, allowing models to be reviewed and approved before deployment. By using the AWS SDK within SageMaker Pipelines, the approval status of a model can be manually changed to 'Approved', ensuring only vetted models are deployed to production endpoints.

Question 4

Which action will meet this requirement? A. Configure the application to invoke an AWS Lambda function that runs a SageMaker Clarify job. B. Invoke an AWS Lambda function to pull the sagemaker-model-monitor-analyzer built-in SageMaker image. C. Use AWS Glue Data Quality to monitor bias. D. Use SageMaker notebooks to compare the bias.
  • A. Configure the application to invoke an AWS Lambda function that runs a SageMaker Clarify job. Correct
  • B. Invoke an AWS Lambda function to pull the sagemaker-model-monitor-analyzer built-in SageMaker image.
  • C. Use AWS Glue Data Quality to monitor bias.
  • D. Use SageMaker notebooks to compare the bias.

Explanation

The correct answer is A because Amazon SageMaker Clarify is specifically designed for detecting and mitigating biases in machine learning models, which aligns with the requirement of monitoring bias drift. Configuring the application to invoke an AWS Lambda function that runs a SageMaker Clarify job allows for automated on-demand bias monitoring as part of the model deployment workflow.

Question 5

HOTSPOT - A company stores historical data in .csv files in Amazon S3. Only some of the rows and columns in the .csv files are populated. The columns are not labeled. An ML engineer needs to prepare and store the data so that the company can use the data to train ML models. Select and order the correct steps from the following list to perform this task. Each step should be selected one time or not at all. (Select and order three.) • Create an Amazon SageMaker batch transform job for data cleaning and feature engineering. • Store the resulting data back in Amazon S3. • Use Amazon Athena to infer the schemas and available columns. • Use AWS Glue crawlers to infer the schemas and available columns. • Use AWS Glue DataBrew for data cleaning and feature engineering.

Explanation

AWS Glue crawlers are used to infer schemas from the .csv files stored in Amazon S3, which is essential given that the columns are not labeled and sparsely populated. AWS Glue DataBrew then enables the ML engineer to perform necessary data cleaning and feature engineering tasks on this inferred schema. Finally, storing the processed data back in Amazon S3 ensures it is ready for use in training ML models.

Question 6

HOTSPOT - An ML engineer needs to use Amazon SageMaker Feature Store to create and manage features to train a model. Select and order the steps from the following list to create and use the features in Feature Store. Each step should be selected one time. (Select and order three.) • Access the store to build datasets for training. • Create a feature group. • Ingest the records.

Explanation

According to AWS documentation, creating and using features in Amazon SageMaker Feature Store involves first defining a schema by creating a feature group, then ingesting data into this defined structure, and finally accessing the stored features to build training datasets. This sequence ensures that the feature store is properly configured before data ingestion and usage for model training.

Question 7

HOTSPOT - A company wants to host an ML model on Amazon SageMaker. An ML engineer is configuring a continuous integration and continuous delivery (Cl/CD) pipeline in AWS CodePipeline to deploy the model. The pipeline must run automatically when new training data for the model is uploaded to an Amazon S3 bucket. Select and order the pipeline's correct steps from the following list. Each step should be selected one time or not at all. (Select and order three.) • An S3 event notification invokes the pipeline when new data is uploaded. • S3 Lifecycle rule invokes the pipeline when new data is uploaded. • SageMaker retrains the model by using the data in the S3 bucket. • The pipeline deploys the model to a SageMaker endpoint. • The pipeline deploys the model to SageMaker Model Registry.

Explanation

An S3 event notification is the appropriate trigger for initiating the CI/CD pipeline when new training data is uploaded, as it directly responds to changes in the S3 bucket. After triggering, SageMaker uses this new data to retrain the model, ensuring that the model remains up-to-date with the latest information. Finally, deploying the updated model to the SageMaker Model Registry facilitates version control and management of different model versions throughout their lifecycle.

Question 8

HOTSPOT - An ML engineer is building a generative AI application on Amazon Bedrock by using large language models (LLMs). Select the correct generative AI term from the following list for each description. Each term should be selected one time or not at all. (Select three.) • Embedding • Retrieval Augmented Generation (RAG) • Temperature • Token

Explanation

According to official AWS documentation, tokens are the basic units of text processed by LLMs, making them the correct representation for fundamental data elements. Embeddings are high-dimensional vectors that capture the semantic meaning of text, aligning with their description as containing textual semantics in a mathematical form. Retrieval Augmented Generation (RAG) enhances generated responses by incorporating information from external sources, fitting the description of enriching responses with additional data.

Question 9

HOTSPOT - An ML engineer is working on an ML model to predict the prices of similarly sized homes. The model will base predictions on several features The ML engineer will use the following feature engineering techniques to estimate the prices of the homes: • Feature splitting • Logarithmic transformation • One-hot encoding • Standardized distribution Select the correct feature engineering techniques for the following list of features. Each feature engineering technique should be selected one time or not at all (Select three.)

Explanation

One-hot encoding is appropriate for categorical data like city names, which cannot be ordered or measured numerically. Feature splitting is suitable for composite features such as "Type_year," where separating the type of home and the year it was built can provide clearer insights to the model. Logarithmic transformation is effective for size measurements, as it helps in handling skewed distributions often found with area measurements, making patterns more visible to the model.

Question 10

Which AWS service or feature can aggregate the data from the various data sources?
  • A. Amazon EMR Spark jobs
  • B. Amazon Kinesis Data Streams
  • C. Amazon DynamoDB
  • D. AWS Lake Formation Correct

Explanation

AWS Lake Formation simplifies the process of building and managing a secure data lake by automating the steps required to move, catalog, transform, and govern your data. It can aggregate data from various sources including Amazon S3 and on-premises databases like MySQL, making it suitable for integrating transaction logs, customer profiles, and on-premises tables.

Question 11

Which solution will meet these requirements?
  • A. Use Amazon Athena to automatically detect the anomalies and to visualize the result.
  • B. Use Amazon Redshift Spectrum to automatically detect the anomalies. Use Amazon QuickSight to visualize the result.
  • C. Use Amazon SageMaker Data Wrangler to automatically detect the anomalies and to visualize the result. Correct
  • D. Use AWS Batch to automatically detect the anomalies. Use Amazon QuickSight to visualize the result.

Explanation

Amazon SageMaker Data Wrangler can be used for data preparation, including anomaly detection, which is necessary for addressing class imbalance and interdependencies in features. Additionally, it supports integration with visualization tools, making it suitable for visualizing the results of anomaly detection.

Question 12

Which action will meet this requirement with the LEAST operational overhead?
  • A. Use AWS Glue to transform the categorical data into numerical data.
  • B. Use AWS Glue to transform the numerical data into categorical data.
  • C. Use Amazon SageMaker Data Wrangler to transform the categorical data into numerical data. Correct
  • D. Use Amazon SageMaker Data Wrangler to transform the numerical data into categorical data.

Explanation

Amazon SageMaker Data Wrangler simplifies the process of preparing data for machine learning by providing a wide range of pre-built data transformations, including converting categorical data into numerical data. This option minimizes operational overhead as it streamlines the preparation and transformation processes necessary to improve model accuracy.

Question 13

Which solution will meet this requirement with the LEAST operational effort? A. Use Amazon Athena to identify patterns that contribute to the imbalance. Adjust the dataset accordingly. B. Use Amazon SageMaker Studio Classic built-in algorithms to process the imbalanced dataset. C. Use AWS Glue DataBrew built-in features to oversample the minority class. D. Use the Amazon SageMaker Data Wrangler balance data operation to oversample the minority class.
  • A. Use Amazon Athena to identify patterns that contribute to the imbalance. Adjust the dataset accordingly.
  • B. Use Amazon SageMaker Studio Classic built-in algorithms to process the imbalanced dataset.
  • C. Use AWS Glue DataBrew built-in features to oversample the minority class.
  • D. Use the Amazon SageMaker Data Wrangler balance data operation to oversample the minority class. Correct

Explanation

Amazon SageMaker Data Wrangler provides a user-friendly interface and pre-built operations for preparing and processing data, including balancing imbalanced datasets through oversampling the minority class with minimal operational effort. This makes it the most efficient solution among the given options to address the issue of class imbalance before training the model.

Question 14

Which algorithm should the ML engineer use to meet this requirement?
  • A. LightGBM Correct
  • B. Linear learner
  • C. К-means clustering
  • D. Neural Topic Model (NTM)

Explanation

LightGBM is suitable for handling datasets with class imbalance and interdependent features, as it can effectively capture complex patterns in the data through gradient boosting techniques. This makes LightGBM a preferable choice over linear learner, K-means clustering, or Neural Topic Model (NTM) for training a fraud detection model on imbalanced datasets with feature interdependencies.

Question 15

A company has deployed an XGBoost prediction model in production to predict if a customer is likely to cancel a subscription. The company uses Amazon SageMaker Model Monitor to detect deviations in the F1 score. During a baseline analysis of model quality, the company recorded a threshold for the F1 score. After several months of no change, the model's F1 score decreases significantly. What could be the reason for the reduced F1 score? Options: A. Concept drift occurred in the underlying customer data that was used for predictions. B. The model was not sufficiently complex to capture all the patterns in the original baseline data. C. The original baseline data had a data quality issue of missing values. D. Incorrect ground truth labels were provided to Model Monitor during the calculation of the baseline.
  • A. Concept drift occurred in the underlying customer data that was used for predictions. Correct
  • B. The model was not sufficiently complex to capture all the patterns in the original baseline data.
  • C. The original baseline data had a data quality issue of missing values.
  • D. Incorrect ground truth labels were provided to Model Monitor during the calculation of the baseline.

Explanation

The correct answer is A because concept drift refers to changes in the underlying patterns of the data over time, which can lead to a decrease in model performance metrics like the F1 score. This aligns with AWS documentation on monitoring and maintaining machine learning models where concept drift is recognized as a common issue affecting model accuracy over time.

Question 16

A company has a team of data scientists who use Amazon SageMaker notebook instances to test ML models. When the data scientists need new permissions, the company attaches the permissions to each individual role that was created during the creation of the SageMaker notebook instance. The company needs to centralize management of the team's permissions. Which solution will meet this requirement? Options: A. Create a single IAM role that has the necessary permissions. Attach the role to each notebook instance that the team uses. B. Create a single IAM group. Add the data scientists to the group. Associate the group with each notebook instance that the team uses. C. Create a single IAM user. Attach the AdministratorAccess AWS managed IAM policy to the user. Configure each notebook instance to use the IAM user. D. Create a single IAM group. Add the data scientists to the group. Create an IAM role. Attach the AdministratorAccess AWS managed IAM policy to the role. Associate the role with the group. Associate the group with each notebook instance that the team uses.
  • A. Create a single IAM role that has the necessary permissions. Attach the role to each notebook instance that the team uses. Correct
  • B. Create a single IAM group. Add the data scientists to the group. Associate the group with each notebook instance that the team uses.
  • C. Create a single IAM user. Attach the AdministratorAccess AWS managed IAM policy to the user. Configure each notebook instance to use the IAM user.
  • D. Create a single IAM group. Add the data scientists to the group. Create an IAM role. Attach the AdministratorAccess AWS managed IAM policy to the role. Associate the role with the group. Associate the group with each notebook instance that the team uses.

Explanation

The correct answer is A because creating a single IAM role with necessary permissions and attaching it to each SageMaker notebook instance centralizes permission management for the data scientists' team, as per AWS best practices. This approach ensures consistent access control without needing individual roles for each user or notebook instance.

Question 17

An ML engineer needs to use an ML model to predict the price of apartments in a specific location. Which metric should the ML engineer use to evaluate the model's performance? Options: A. Accuracy B. Area Under the ROC Curve (AUC) C. F1 score D. Mean absolute error (MAE)
  • A. Accuracy
  • B. Area Under the ROC Curve (AUC)
  • C. F1 score
  • D. Mean absolute error (MAE) Correct

Explanation

The correct answer is D, Mean Absolute Error (MAE). This metric is appropriate for regression tasks where the goal is to predict a continuous value, such as apartment prices. MAE measures the average magnitude of errors between predicted and actual values without considering their direction, making it suitable for evaluating model performance in this context.

Question 18

An ML engineer has trained a neural network by using stochastic gradient descent (SGD). The neural network performs poorly on the test set. The values for training loss and validation loss remain high and show an oscillating pattern. The values decrease for a few epochs and then increase for a few epochs before repeating the same cycle. What should the ML engineer do to improve the training process? Options: A. Introduce early stopping. B. Increase the size of the test set. C. Increase the learning rate. D. Decrease the learning rate.
  • A. Introduce early stopping.
  • B. Increase the size of the test set.
  • C. Increase the learning rate.
  • D. Decrease the learning rate. Correct

Explanation

The correct answer is D because decreasing the learning rate can help stabilize the training process and reduce the oscillating pattern observed in both training loss and validation loss, leading to potentially better performance on the test set according to AWS documentation.

Question 19

An ML engineer needs to process thousands of existing CSV objects and new CSV objects that are uploaded. The CSV objects are stored in a central Amazon S3 bucket and have the same number of columns. One of the columns is a transaction date. The ML engineer must query the data based on the transaction date. Which solution will meet these requirements with the LEAST operational overhead? Options: A. Use an Amazon Athena CREATE TABLE AS SELECT (CTAS) statement to create a table based on the transaction date from data in the central S3 bucket. Query the objects from the table. B. Create a new S3 bucket for processed data. Set up S3 replication from the central S3 bucket to the new S3 bucket. Use S3 Object Lambda to query the objects based on transaction date. C. Create a new S3 bucket for processed data. Use AWS Glue for Apache Spark to create a job to query the CSV objects based on transaction date. Configure the job to store the results in the new S3 bucket. Query the objects from the new S3 bucket. D. Create a new S3 bucket for processed data. Use Amazon Data Firehose to transfer the data from the central S3 bucket to the new S3 bucket. Configure Firehose to run an AWS Lambda function to query the data based on transaction date.
  • A. Use an Amazon Athena CREATE TABLE AS SELECT (CTAS) statement to create a table based on the transaction date from data in the central S3 bucket. Query the objects from the table. Correct
  • B. Create a new S3 bucket for processed data. Set up S3 replication from the central S3 bucket to the new S3 bucket. Use S3 Object Lambda to query the objects based on transaction date.
  • C. Create a new S3 bucket for processed data. Use AWS Glue for Apache Spark to create a job to query the CSV objects based on transaction date. Configure the job to store the results in the new S3 bucket. Query the objects from the new S3 bucket.
  • D. Create a new S3 bucket for processed data. Use Amazon Data Firehose to transfer the data from the central S3 bucket to the new S3 bucket. Configure Firehose to run an AWS Lambda function to query the data based on transaction date.

Explanation

Option A is correct because using Amazon Athena with a CREATE TABLE AS SELECT (CTAS) statement allows for direct querying of CSV objects stored in an S3 bucket without requiring additional processing or setup. This approach minimizes operational overhead as it leverages the existing data and infrastructure, enabling efficient querying based on the transaction date.

Question 20

A company has a large, unstructured dataset. The dataset includes many duplicate records across several key attributes. Which solution on AWS will detect duplicates in the dataset with the LEAST code development? Options: A. Use Amazon Mechanical Turk jobs to detect duplicates. B. Use Amazon QuickSight ML Insights to build a custom deduplication model. C. Use Amazon SageMaker Data Wrangler to pre-process and detect duplicates. D. Use the AWS Glue FindMatches transform to detect duplicates.
  • A. Use Amazon Mechanical Turk jobs to detect duplicates.
  • B. Use Amazon QuickSight ML Insights to build a custom deduplication model.
  • C. Use Amazon SageMaker Data Wrangler to pre-process and detect duplicates.
  • D. Use the AWS Glue FindMatches transform to detect duplicates. Correct

Explanation

The correct answer is D because AWS Glue's FindMatches transform is specifically designed for detecting duplicate records in datasets with minimal code development, aligning with the requirement of least code development. This feature leverages machine learning to identify and group similar records based on specified attributes without needing extensive custom coding or manual intervention.

Verifying access...