Question 1

An ML engineer trained an ML model on Amazon SageMaker to detect automobile accidents from dosed-circuit TV footage. The ML engineer used SageMaker Data Wrangler to create a training dataset of images of accidents and non-accidents. The model performed well during training and validation. However, the model is underperforming in production because of variations in the quality of the images from various cameras. Which solution will improve the model's accuracy in the LEAST amount of time? 

A. Collect more images from all the cameras. Use Data Wrangler to prepare a new training dataset. 

B. Recreate the training dataset by using the Data Wrangler corrupt image transform. Specify the impulse noise option. 

C. Recreate the training dataset by using the Data Wrangler enhance image contrast transform. Specify the Gamma contrast option. 

D. Recreate the training dataset by using the Data Wrangler resize image transform. Crop all images to the same size. 

Answer: B

Question 2

Case study An ML engineer is developing a fraud detection model on AWS. The training dataset includes transaction logs, customer profiles, and tables from an on-premises MySQL database. The transaction logs and customer profiles are stored in Amazon S3. The dataset has a class imbalance that affects the learning of the model's algorithm. Additionally, many of the features have interdependencies. The algorithm is not capturing all the desired underlying patterns in the data. Before the ML engineer trains the model, the ML engineer must resolve the issue of the imbalanced data. 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. 

Answer: D

Question 3

A company is developing an ML model by using Amazon SageMaker AI. The company must monitor bias in the model and display the results on a dashboard. An ML engineer creates a bias monitoring job. How should the ML engineer capture bias metrics to display on the dashboard?

A. Capture AWS CloudTrail metrics from SageMaker Clarify. 

B. Capture Amazon CloudWatch metrics from SageMaker Clarify. 

C. Capture SageMaker Model Monitor metrics from Amazon EventBridge. 

D. Capture SageMaker Model Monitor metrics from Amazon SNS. 

Answer: B

Question 4

An ML engineer is training an XGBoost regression model in Amazon SageMaker AI. The ML engineer conducts several rounds of hyperparameter tuning with random grid search. After these rounds of tuning, the error rate on the test hold-out dataset is much larger than the error rate on the training dataset. The ML engineer needs to make changes before running the hyperparameter grid search again. Which changes will improve the model's performance? (Select TWO.) 

A. Increase the model complexity by increasing the number of features in the dataset. 

B. Decrease the model complexity by reducing the number of features in the dataset. 

C. Decrease the model complexity by reducing the number of samples in the dataset. 

D. Increase the value of the L2 regularization parameter. 

E. Decrease the value of the L2 regularization parameter. 

Answer: B,D

Question 5

A company needs to run a batch data-processing job on Amazon EC2 instances. The job will run during the weekend and will take 90 minutes to finish running. The processing can handle interruptions. The company will run the job every weekend for the next 6 months. Which EC2 instance purchasing option will meet these requirements MOST costeffectively?

A. Spot Instances 

B. Reserved Instances 

C. On-Demand Instances 

D. Dedicated Instances 

Answer: A