Microsoft Microsoft Certifications AI-100 Questions & Answers

• Question 131:

  You are designing an Azure Batch AI solution that will perform image recognition. The solution will be used to train several Azure Machine Learning models.

  You need to enable versioning for Azure Machine Learning models.

  What should you do?

  A. Register the Azure Machine Learning models.

  B. Use Azure HDInsight cluster.

  C. Use Machine Learning experiments.

  D. Use Machine Learning pipelines.

  Correct Answer: A

  Model registration allows you to store and version your models in the Azure cloud, in your workspace. The model registry makes it easy to organize and keep track of your trained models.

  Reference:

  https://docs.microsoft.com/en-us/azure/machine-learning/studio/version-control https://docs.microsoft.com/en-us/azure/machine-learning/how-to-deploy-and-where

• Question 132:

  You are developing an AI solution that will use in-memory caching and a columnar storage engine for Apache Hive queries. What HDInsight platform should you use?

  A. Apache Kafka

  B. Apache Spark

  C. Interactive Query

  D. Apache Storm

  Correct Answer: C

  Interactive Query provides In-memory caching and improved columnar storage engine for Hive queries. Reference: https://docs.microsoft.com/bs-latn-ba/azure/hdinsight/interactive-query/apache-interactive-query-get-started

• Question 133:

  You are developing an application that uses an API pipeline. The application consumes and analyzes streaming data.

  You API pipeline must perform face detection and sentiment analysis.

  What actions should you take?

  A. Use the Computer Vision API in the pipeline.

  B. Use the Face API in the pipeline.

  C. Use the Text Analytics in the pipeline.

  D. Use the Video Indexer in the pipeline.

  Correct Answer: B

  To perform face detection and sentiment analysis in the API pipeline for analyzing streaming data, you should take the following actions:

  Use the Face API in the pipeline: The Face API provides facial detection and analysis capabilities, allowing you to detect faces in images or video frames, extract facial attributes, and perform facial recognition. This will enable you to perform

  face detection as part of your API pipeline.

• Question 134:

  You company's developers have created an Azure Data Factory pipeline that moves data from an on-premises server to Azure Storage. The pipeline consumes

  Azure Cognitive Services APIs.

  You need to deploy the pipeline. Your solution must minimize custom code.

  You use Integration Runtime to move data to the cloud and Azure API Management to consume Cognitive Services APIs.

  Does this action accomplish your objective?

  A. Yes, it does

  B. No, it does not

  Correct Answer: B

  The given solution does not accomplish the objective of minimizing custom code. While Integration Runtime can be used to move data from an on-premises server to Azure Storage, and Azure API Management can be used to consume

  Cognitive Services APIs, it does not eliminate the need for custom code.

  To minimize custom code and simplify the deployment of the pipeline, you should consider using Azure Logic Apps. Azure Logic Apps provide a serverless and code-free way to orchestrate workflows and integrate different systems and

  services.

  Reference:

  https://docs.microsoft.com/en-us/azure/data-factory/concepts-integration-runtime https://docs.microsoft.com/en-us/azure/logic-apps/logic-apps-examples-and-scenarios

• Question 135:

  You have created an AI solution that uses several PersonGroup objects.

  One of the PersonGroup objects contains thousands of entries and cannot accept any new entries.

  You want to be able to add new entries to the PersonGroup object. The PersonGroup object must be identifiable by all the entries.

  Which of the following actions should you take?

  A. Compress the entries from the PersonGroup object.

  B. Create another PersonGroup object with the same name.

  C. Migrate the PersonGroup to a LargePersonGroup object.

  D. Archive some of the entries from the PersonGroup object.

  Correct Answer: C

  LargePersonGroup and LargeFaceList are collectively referred to as large-scale operations. LargePersonGroup can contain up to 1 million persons, each with a maximum of 248 faces. LargeFaceList can contain up to 1 million faces. The

  large-scale operations are similar to the conventional PersonGroup and FaceList but have some differences because of the new architecture.

  Reference:

  https://docs.microsoft.com/en-us/azure/cognitive-services/face/face-api-how-to-topics/how-to-use-large-scale

• Question 136:

  You company's developers have created an Azure Data Factory pipeline that moves data from an on-premises server to Azure Storage. The pipeline consumes

  Azure Cognitive Services APIs.

  You need to deploy the pipeline. Your solution must minimize custom code.

  You use Azure-SSIS Integration Runtime (IR) to move data to the cloud and Azure API Apps to consume Cognitive Services APIs.

  Does this action accomplish your objective?

  A. Yes, it does

  B. No, it does not

  Correct Answer: B

  With Azure-SSIS Integration Runtime you would need to write custom code Reference: https://docs.microsoft.com/en-us/azure/data-factory/concepts-integration-runtime https://docs.microsoft.com/en-us/azure/logic-apps/logic-apps-examples-and-scenarios

• Question 137:

  You are developing an app that consumes data from several Azure IoT Edge devices.

  You need to implement a storage solution for the app. Your solution must allow data to be queried in real-time as it streams into the solution. You need to ensure that your solution provides the least amount of latency for loading data.

  You want the data files to persist on the devices for at least 14 days.

  What storage solution should you implement?

  A. Azure Data Lake Analytics

  B. Azure Data Factory Edge

  C. Azure HDInsight Hadoop cluster

  D. Azure SQL database with In-Memory OLTP

  Correct Answer: B

  To implement a storage solution that allows real-time querying of data with low latency and ensures data persistence on the devices for at least 14 days, you should use Azure Data Factory Edge.

  Azure Data Factory Edge is designed to collect, transform, and analyze data from edge devices. It provides a scalable and reliable solution for ingesting, processing, and storing data at the edge. With Azure Data Factory Edge, you can configure data flows to ingest data from your Azure IoT Edge devices and store it in the desired storage format (e.g., Azure Blob storage, Azure Data Lake Storage).

  By using Azure Data Factory Edge, you can set up data pipelines to stream and process the data in real-time, allowing you to query the data as it streams into the solution with minimal latency. Additionally, you can define retention policies to ensure that the data files persist on the devices for at least 14 days.

• Question 138:

  You are developing the workflow for an Azure Machine Learning solution. The solution must retrieve data from the following on-premises sources:

  Windows Server 2016 File servers

  Microsoft SQL Server databases

  Oracle databases Which of the following actions should you take?

  A. Make use of Azure Data Factory to retrieve the data.

  B. Make use of Azure Databricks to retrieve the data.

  C. Make use of Azure Stream Analytics to retrieve the data.

  D. Make use of Azure Synapse Analytics to retrieve the data.

  Correct Answer: A

  Azure Data Factory is a cloud-based data integration service that allows you to orchestrate and automate the movement and transformation of data from various sources, including on-premises sources, to your desired destinations. It provides connectivity options and data integration capabilities to pull data from on-premises sources and load it into Azure for further processing and analysis in your Azure Machine Learning workflow.

• Question 139:

  You are designing an Azure Batch AI solution that will perform image recognition. The solution will be used to train several Azure Machine Learning models.

  You need to recommend a compute infrastructure for the solution that minimizes the processing time.

  What should you recommend?

  A. Compute optimized virtual machines.

  B. Memory optimized virtual machines.

  C. GPU optimized virtual machines.

  D. General purpose virtual machines.

  Correct Answer: C

  GPU optimized virtual machines are specialized virtual machines targeted for heavy graphic rendering and video editing, as well as model training and inferencing

  (ND) with deep learning.

  Reference:

  https://docs.microsoft.com/en-us/azure/virtual-machines/windows/sizes-gpu

• Question 140:

  You are developing a bot for an ecommerce application.

  You must implement user authentication for the bot. You want the authentication process to be encrypted.

  What actions should you take?

  A. Make use of NTLM and smart cards

  B. Make use of SSL/TLS and JSON Web Token (JWT)

  C. Make use of API keys and access keys

  D. Make use of HTTPS and Kerberos

  Correct Answer: B

  Your bot communicates with the Bot Connector service using HTTP over a secured channel (SSL/TLS).

  JSON Web Tokens are used to encode tokens that are sent to and from the bot.

  Reference:

  https://docs.microsoft.com/en-us/azure/bot-service/rest-api/bot-framework-rest-connector-authentication