Amazon MLS-C01 Exam Dumps

AWS Certified Machine Learning - Specialty

Amazon MLS-C01 Sample Questions

Question # 1

A company is building a demand forecasting model based on machine learning (ML). In thedevelopment stage, an ML specialist uses an Amazon SageMaker notebook to performfeature engineering during work hours that consumes low amounts of CPU and memoryresources. A data engineer uses the same notebook to perform data preprocessing once aday on average that requires very high memory and completes in only 2 hours. The datapreprocessing is not configured to use GPU. All the processes are running well on anml.m5.4xlarge notebook instance.The company receives an AWS Budgets alert that the billing for this month exceeds theallocated budget.Which solution will result in the MOST cost savings?

A. Change the notebook instance type to a memory optimized instance with the samevCPU number as the ml.m5.4xlarge instance has. Stop the notebook when it is not in use.Run both data preprocessing and feature engineering development on that instance. 
B. Keep the notebook instance type and size the same. Stop the notebook when it is not inuse. Run data preprocessing on a P3 instance type with the same memory as theml.m5.4xlarge instance by using Amazon SageMaker Processing. 
C. Change the notebook instance type to a smaller general purpose instance. Stop thenotebook when it is not in use. Run data preprocessing on an ml.r5 instance with the samememory size as the ml.m5.4xlarge instance by using Amazon SageMaker Processing. 
D. Change the notebook instance type to a smaller general purpose instance. Stop thenotebook when it is not in use. Run data preprocessing on an R5 instance with the samememory size as the ml.m5.4xlarge instance by using the Reserved Instance option. 

Show Answer

Question # 2

A manufacturing company wants to use machine learning (ML) to automate quality controlin its facilities. The facilities are in remote locations and have limited internet connectivity.The company has 20 of training data that consists of labeled images of defective productparts. The training data is in the corporate on-premises data center.The company will use this data to train a model for real-time defect detection in new partsas the parts move on a conveyor belt in the facilities. The company needs a solution thatminimizes costs for compute infrastructure and that maximizes the scalability of resourcesfor training. The solution also must facilitate the company’s use of an ML model in the lowconnectivity environments.Which solution will meet these requirements?

A. Move the training data to an Amazon S3 bucket. Train and evaluate the model by usingAmazon SageMaker. Optimize the model by using SageMaker Neo. Deploy the model on aSageMaker hosting services endpoint. 
B. Train and evaluate the model on premises. Upload the model to an Amazon S3 bucket.Deploy the model on an Amazon SageMaker hosting services endpoint. 
C. Move the training data to an Amazon S3 bucket. Train and evaluate the model by usingAmazon SageMaker. Optimize the model by using SageMaker Neo. Set up an edge devicein the manufacturing facilities with AWS IoT Greengrass. Deploy the model on the edgedevice. 
D. Train the model on premises. Upload the model to an Amazon S3 bucket. Set up anedge device in the manufacturing facilities with AWS IoT Greengrass. Deploy the model onthe edge device. 

Show Answer

Question # 3

A company is building a predictive maintenance model based on machine learning (ML).The data is stored in a fully private Amazon S3 bucket that is encrypted at rest with AWSKey Management Service (AWS KMS) CMKs. An ML specialist must run datapreprocessing by using an Amazon SageMaker Processing job that is triggered from codein an Amazon SageMaker notebook. The job should read data from Amazon S3, process it,and upload it back to the same S3 bucket. The preprocessing code is stored in a containerimage in Amazon Elastic Container Registry (Amazon ECR). The ML specialist needs togrant permissions to ensure a smooth data preprocessing workflowWhich set of actions should the ML specialist take to meet these requirements?

A. Create an IAM role that has permissions to create Amazon SageMaker Processing jobs,S3 read and write access to the relevant S3 bucket, and appropriate KMS and ECRpermissions. Attach the role to the SageMaker notebook instance. Create an AmazonSageMaker Processing job from the notebook. 
B. Create an IAM role that has permissions to create Amazon SageMaker Processing jobs.Attach the role to the SageMaker notebook instance. Create an Amazon SageMakerProcessing job with an IAM role that has read and write permissions to the relevant S3bucket, and appropriate KMS and ECR permissions. 
C. Create an IAM role that has permissions to create Amazon SageMaker Processing jobsand to access Amazon ECR. Attach the role to the SageMaker notebook instance. Set upboth an S3 endpoint and a KMS endpoint in the default VPC. Create Amazon SageMakerProcessing jobs from the notebook. 
D. Create an IAM role that has permissions to create Amazon SageMaker Processing jobs.Attach the role to the SageMaker notebook instance. Set up an S3 endpoint in the defaultVPC. Create Amazon SageMaker Processing jobs with the access key and secret key ofthe IAM user with appropriate KMS and ECR permissions. 

Show Answer

Question # 4

A machine learning specialist is developing a proof of concept for government users whoseprimary concern is security. The specialist is using Amazon SageMaker to train aconvolutional neural network (CNN) model for a photo classifier application. The specialistwants to protect the data so that it cannot be accessed and transferred to a remote host bymalicious code accidentally installed on the training container.Which action will provide the MOST secure protection?

A. Remove Amazon S3 access permissions from the SageMaker execution role. 
B. Encrypt the weights of the CNN model. 
C. Encrypt the training and validation dataset. 
D. Enable network isolation for training jobs. 

Show Answer

Question # 5

A company wants to create a data repository in the AWS Cloud for machine learning (ML)projects. The company wants to use AWS to perform complete ML lifecycles and wants touse Amazon S3 for the data storage. All of the company’s data currently resides onpremises and is 40 in size.The company wants a solution that can transfer and automatically update data between theon-premises object storage and Amazon S3. The solution must support encryption,scheduling, monitoring, and data integrity validation.Which solution meets these requirements?

A. Use the S3 sync command to compare the source S3 bucket and the destination S3bucket. Determine which source files do not exist in the destination S3 bucket and whichsource files were modified. 
B. Use AWS Transfer for FTPS to transfer the files from the on-premises storage toAmazon S3. 
C. Use AWS DataSync to make an initial copy of the entire dataset. Schedule subsequentincremental transfers of changing data until the final cutover from on premises to AWS. 
D. Use S3 Batch Operations to pull data periodically from the on-premises storage. EnableS3 Versioning on the S3 bucket to protect against accidental overwrites. 

Show Answer

Question # 6

A machine learning (ML) specialist must develop a classification model for a financialservices company. A domain expert provides the dataset, which is tabular with 10,000 rowsand 1,020 features. During exploratory data analysis, the specialist finds no missing valuesand a small percentage of duplicate rows. There are correlation scores of > 0.9 for 200feature pairs. The mean value of each feature is similar to its 50th percentile.Which feature engineering strategy should the ML specialist use with Amazon SageMaker?

A. Apply dimensionality reduction by using the principal component analysis (PCA)algorithm. 
B. Drop the features with low correlation scores by using a Jupyter notebook. 
C. Apply anomaly detection by using the Random Cut Forest (RCF) algorithm. 
D. Concatenate the features with high correlation scores by using a Jupyter notebook. 

Show Answer

Question # 7

A Machine Learning Specialist is designing a scalable data storage solution for AmazonSageMaker. There is an existing TensorFlow-based model implemented as a train.py scriptthat relies on static training data that is currently stored as TFRecordsWhich method of providing training data to Amazon SageMaker would meet the businessrequirements with the LEAST development overhead?

A. Use Amazon SageMaker script mode and use train.py unchanged. Point the AmazonSageMaker training invocation to the local path of the data without reformatting the trainingdata. 
B. Use Amazon SageMaker script mode and use train.py unchanged. Put the TFRecorddata into an Amazon S3 bucket. Point the Amazon SageMaker training invocation to the S3bucket without reformatting the training data. 
C. Rewrite the train.py script to add a section that converts TFRecords to protobuf andingests the protobuf data instead of TFRecords. 
D. Prepare the data in the format accepted by Amazon SageMaker. Use AWS Glue orAWS Lambda to reformat and store the data in an Amazon S3 bucket. 

Show Answer

Question # 8

A data scientist is using the Amazon SageMaker Neural Topic Model (NTM) algorithm tobuild a model that recommends tags from blog posts. The raw blog post data is stored inan Amazon S3 bucket in JSON format. During model evaluation, the data scientistdiscovered that the model recommends certain stopwords such as "a," "an,” and "the" astags to certain blog posts, along with a few rare words that are present only in certain blogentries. After a few iterations of tag review with the content team, the data scientist noticesthat the rare words are unusual but feasible. The data scientist also must ensure that thetag recommendations of the generated model do not include the stopwords.What should the data scientist do to meet these requirements?

A. Use the Amazon Comprehend entity recognition API operations. Remove the detectedwords from the blog post data. Replace the blog post data source in the S3 bucket. 
B. Run the SageMaker built-in principal component analysis (PCA) algorithm with the blogpost data from the S3 bucket as the data source. Replace the blog post data in the S3bucket with the results of the training job. 
C. Use the SageMaker built-in Object Detection algorithm instead of the NTM algorithm forthe training job to process the blog post data. 
D. Remove the stopwords from the blog post data by using the Count Vectorizer function inthe scikit-learn library. Replace the blog post data in the S3 bucket with the results of thevectorizer. 

Show Answer

Question # 9

A Data Scientist received a set of insurance records, each consisting of a record ID, thefinal outcome among200 categories, and the date of the final outcome. Some partial information on claimcontents is also provided,but only for a few of the 200 categories. For each outcome category, there are hundreds ofrecords distributedover the past 3 years. The Data Scientist wants to predict how many claims to expect ineach category from month to month, a few months in advance.What type of machine learning model should be used?

A. Classification month-to-month using supervised learning of the 200 categories based onclaim contents. 
B. Reinforcement learning using claim IDs and timestamps where the agent will identifyhow many claims in each category to expect from month to month. 
C. Forecasting using claim IDs and timestamps to identify how many claims in eachcategory to expect from month to month. 
D. Classification with supervised learning of the categories for which partial information onclaim contents is provided, and forecasting using claim IDs and timestamps for all other categories. 

Show Answer

Question # 10

A Machine Learning Specialist uploads a dataset to an Amazon S3 bucket protected withserver-sideencryption using AWS KMS.How should the ML Specialist define the Amazon SageMaker notebook instance so it canread the samedataset from Amazon S3?

A. Define security group(s) to allow all HTTP inbound/outbound traffic and assign thosesecurity group(s) to the Amazon SageMaker notebook instance. 
B. onfigure the Amazon SageMaker notebook instance to have access to the VPC. Grantpermission in the KMS key policy to the notebook’s KMS role. 
C. Assign an IAM role to the Amazon SageMaker notebook with S3 read access to thedataset. Grant permission in the KMS key policy to that role. 
D. Assign the same KMS key used to encrypt data in Amazon S3 to the AmazonSageMaker notebook instance. 

Show Answer

Question # 11

A company provisions Amazon SageMaker notebook instances for its data science teamand creates Amazon VPC interface endpoints to ensure communication between the VPCand the notebook instances. All connections to the Amazon SageMaker API are containedentirely and securely using the AWS network. However, the data science team realizes thatindividuals outside the VPC can still connect to the notebook instances across the internet.Which set of actions should the data science team take to fix the issue?

A. Modify the notebook instances' security group to allow traffic only from the CIDR rangesof the VPC. Apply this security group to all of the notebook instances' VPC interfaces. 
B. Create an IAM policy that allows the sagemaker:CreatePresignedNotebooklnstanceUrland sagemaker:DescribeNotebooklnstance actions from only the VPC endpoints. Applythis policy to all IAM users, groups, and roles used to access the notebook instances. 
C. Add a NAT gateway to the VPC. Convert all of the subnets where the AmazonSageMaker notebook instances are hosted to private subnets. Stop and start all of thenotebook instances to reassign only private IP addresses. 
D. Change the network ACL of the subnet the notebook is hosted in to restrict access toanyone outside the VPC. 

Show Answer

Question # 12

A data scientist is working on a public sector project for an urban traffic system. Whilestudying the traffic patterns, it is clear to the data scientist that the traffic behavior at eachlight is correlated, subject to a small stochastic error term. The data scientist must modelthe traffic behavior to analyze the traffic patterns and reduce congestionHow will the data scientist MOST effectively model the problem?

A. The data scientist should obtain a correlated equilibrium policy by formulating thisproblem as a multi-agent reinforcement learning problem. 
B. The data scientist should obtain the optimal equilibrium policy by formulating thisproblem as a single-agent reinforcement learning problem. 
C. Rather than finding an equilibrium policy, the data scientist should obtain accuratepredictors of traffic flow by using historical data through a supervised learning approach. 
D. Rather than finding an equilibrium policy, the data scientist should obtain accuratepredictors of traffic flow by using unlabeled simulated data representing the new trafficpatterns in the city and applying an unsupervised learning approach. 

Show Answer

Question # 13

A company is converting a large number of unstructured paper receipts into images. Thecompany wants to create a model based on natural language processing (NLP) to findrelevant entities such as date, location, and notes, as well as some custom entities such asreceipt numbers.The company is using optical character recognition (OCR) to extract text for data labeling.However, documents are in different structures and formats, and the company is facingchallenges with setting up the manual workflows for each document type. Additionally, thecompany trained a named entity recognition (NER) model for custom entity detection usinga small sample size. This model has a very low confidence score and will require retrainingwith a large dataset.Which solution for text extraction and entity detection will require the LEAST amount ofeffort?

A. Extract text from receipt images by using Amazon Textract. Use the AmazonSageMaker BlazingText algorithm to train on the text for entities and custom entities. 
B. Extract text from receipt images by using a deep learning OCR model from the AWSMarketplace. Use the NER deep learning model to extract entities. 
C. Extract text from receipt images by using Amazon Textract. Use Amazon Comprehendfor entity detection, and use Amazon Comprehend custom entity recognition for customentity detection. 
D. Extract text from receipt images by using a deep learning OCR model from the AWSMarketplace. Use Amazon Comprehend for entity detection, and use Amazon Comprehendcustom entity recognition for custom entity detection. 

Show Answer

Question # 14

A company has set up and deployed its machine learning (ML) model into production withan endpoint using Amazon SageMaker hosting services. The ML team has configuredautomatic scaling for its SageMaker instances to support workload changes. During testing,the team notices that additional instances are being launched before the new instances areready. This behavior needs to change as soon as possible.How can the ML team solve this issue?

A. Decrease the cooldown period for the scale-in activity. Increase the configuredmaximum capacity of instances. 
B. Replace the current endpoint with a multi-model endpoint using SageMaker. 
C. Set up Amazon API Gateway and AWS Lambda to trigger the SageMaker inferenceendpoint. 
D. Increase the cooldown period for the scale-out activity. 

Show Answer

Question # 15

A power company wants to forecast future energy consumption for its customers inresidential properties and commercial business properties. Historical power consumptiondata for the last 10 years is available. A team of data scientists who performed the initialdata analysis and feature selection will include the historical power consumption data anddata such as weather, number of individuals on the property, and public holidays.The data scientists are using Amazon Forecast to generate the forecasts.Which algorithm in Forecast should the data scientists use to meet these requirements?

A. Autoregressive Integrated Moving Average (AIRMA) 
B. Exponential Smoothing (ETS) 
C. Convolutional Neural Network - Quantile Regression (CNN-QR) 
D. Prophet 

Show Answer