Amazon MLA-C01 Question Answers

Question # 41

An ML engineer wants to run a training job on Amazon SageMaker AI. The training job will train a neural network by using multiple GPUs. The training dataset is stored in Parquet format. The ML engineer discovered that the Parquet dataset contains files too large to fit into the memory of the SageMaker AI training instances. Which solution will fix the memory problem?

A. Attach an Amazon Elastic Block Store (Amazon EBS) Provisioned IOPS SSD volume to the instance. Store the files in the EBS volume. 
B. Repartition the Parquet files by using Apache Spark on Amazon EMR. Use the repartitioned files for the training job. 
C. Change the instance type to Memory Optimized instances with sufficient memory for the training job. 
D. Use the SageMaker AI distributed data parallelism (SMDDP) library with multiple instances to split the memory usage. 

Show / Hide Answer

---

Question # 42

An ML engineer has developed a binary classification model outside of Amazon SageMaker. The ML engineer needs to make the model accessible to a SageMaker Canvas user for additional tuning. The model artifacts are stored in an Amazon S3 bucket. The ML engineer and the Canvas user are part of the same SageMaker domain. Which combination of requirements must be met so that the ML engineer can share the model with the Canvas user? (Choose two.)

A. The ML engineer and the Canvas user must be in separate SageMaker domains.
 B. The Canvas user must have permissions to access the S3 bucket where the model artifacts are stored. 
C. The model must be registered in the SageMaker Model Registry. 
D. The ML engineer must host the model on AWS Marketplace. 
E. The ML engineer must deploy the model to a SageMaker endpoint. 

Show / Hide Answer

---

Question # 43

An ML engineer is using an Amazon SageMaker Studio notebook to train a neural network by creating an estimator. The estimator runs a Python training script that uses Distributed Data Parallel (DDP) on a single instance that has more than one GPU. The ML engineer discovers that the training script is underutilizing GPU resources. The ML engineer must identify the point in the training script where resource utilization can be optimized. Which solution will meet this requirement?

A. Use Amazon CloudWatch metrics to create a report that describes GPU utilization over time. 
B. Add SageMaker Profiler annotations to the training script. Run the script and generate a report from the results. 
C. Use AWS CloudTrail to create a report that describes GPU utilization and GPU memory utilization over time. 
D. Create a default monitor in Amazon SageMaker Model Monitor and suggest a baseline. Generate a report based on the constraints and statistics the monitor generates. 

Show / Hide Answer

---

Question # 44

An ML engineer receives datasets that contain missing values, duplicates, and extreme outliers. The ML engineer must consolidate these datasets into a single data frame and must prepare the data for ML. Which solution will meet these requirements?

A. Use Amazon SageMaker Data Wrangler to import the datasets and to consolidate them into a single data frame. Use the cleansing and enrichment functionalities to prepare the data. 
B. Use Amazon SageMaker Ground Truth to import the datasets and to consolidate them into a single data frame. Use the human-in-the-loop capability to prepare the data. 
C. Manually import and merge the datasets. Consolidate the datasets into a single data frame. Use Amazon Q Developer to generate code snippets that will prepare the data. 
D. Manually import and merge the datasets. Consolidate the datasets into a single data frame. Use Amazon SageMaker data labeling to prepare the data. 

Show / Hide Answer

---

Question # 45

A gaming company needs to deploy a natural language processing (NLP) model to moderate a chat forum in a game. The workload experiences heavy usage during evenings and weekends but minimal activity during other hours. Which solution will meet these requirements MOST cost-effectively?

A. Use an Amazon SageMaker AI batch transform job with fixed capacity. 
B. Use Amazon SageMaker Serverless Inference. 
C. Use a single Amazon EC2 GPU instance with reserved capacity. 
D. Use Amazon SageMaker Asynchronous Inference. 

Show / Hide Answer

---

Question # 46

A customer call center uses Amazon Transcribe to convert hundreds of audio recordings of conversations between customers and support agents to text files. The call center wants to use the text files to train an ML model. To comply with industry regulations, the call center must remove customer names, addresses, and phone numbers from the training text files. Which solution will meet these requirements with the LEAST development effort?

A. Use Amazon Bedrock Guardrails to process and redact personal information from the text files. 
B. Use the AWS Glue Detect PII transform to remove personal information from the text files. 
C. Store the text files in Amazon S3 buckets. Use S3 Object Lambda functions to redact personal information. 
D. Configure an Amazon SageMaker Data Wrangler custom transformation to remove personal information from the text files. 

Show / Hide Answer

---

Question # 47

A company is developing a generative AI conversational interface to assist customers with payments. The company wants to use an ML solution to detect customer intent. The company does not have training data to train a model. Which solution will meet these requirements?

A. Fine-tune a sequence-to-sequence (seq2seq) algorithm in Amazon SageMaker JumpStart. 
B. Use an LLM from Amazon Bedrock with zero-shot learning. 
C. Use the Amazon Comprehend DetectEntities API.
 D. Run an LLM from Amazon Bedrock on Amazon EC2 instances. 

Show / Hide Answer

---

Question # 48

A company uses an Amazon EMR cluster to run a data ingestion process for an ML model. An ML engineer notices that the processing time is increasing. Which solution will reduce the processing time MOST cost-effectively? 

A. Use Spot Instances to increase the number of primary nodes. 
B. Use Spot Instances to increase the number of core nodes. 
C. Use Spot Instances to increase the number of task nodes.
 D. Use On-Demand Instances to increase the number of core nodes. 

Show / Hide Answer

---

Question # 49

A company wants to share data with a vendor in real time to improve the performance of the vendor's ML models. The vendor needs to ingest the data in a stream. The vendor will use only some of the columns from the streamed data. Which solution will meet these requirements?

A. Use AWS Data Exchange to stream the data to an Amazon S3 bucket. Use an Amazon Athena CREATE TABLE AS SELECT (CTAS) query to define relevant columns.
 B. Use Amazon Kinesis Data Streams to ingest the data. Use Amazon Managed Service for Apache Flink as a consumer to extract relevant columns. 
C. Create an Amazon S3 bucket. Configure the S3 bucket policy to allow the vendor to upload data to the S3 bucket. Configure the S3 bucket policy to control which columns are shared. 
D. Use AWS Lake Formation to ingest the data. Use the column-level filtering feature in Lake Formation to extract relevant columns. 

Show / Hide Answer

---

Question # 50

An ML engineer is using Amazon SageMaker Canvas to build a custom ML model from an imported dataset. The model must make continuous numeric predictions based on 10 years of data. Which metric should the ML engineer use to evaluate the model’s performance?

A. Accuracy 
B. InferenceLatency 
C. Area Under the ROC Curve (AUC) 
D. Root Mean Square Error (RMSE) 

Show / Hide Answer

---

<123456789>

---

Download All 241 Questions Check Customers Feedbacks