Microsoft Microsoft Certifications AI-100 Questions & Answers

• Question 71:

  Your company has a data team of Scala and R experts.

  You plan to ingest data from multiple Apache Kafka streams.

  You need to recommend a processing technology to broker messages at scale from Kafka streams to Azure Storage.

  What should you recommend?

  A. Azure Databricks

  B. Azure Functions

  C. Azure HDInsight with Apache Storm

  D. Azure HDInsight with Microsoft Machine Learning Server

  Correct Answer: C

  References: https://docs.microsoft.com/en-us/azure/hdinsight/hdinsight-streaming-at-scale-overview?toc=https%3A%2F%2Fdocs.microsoft.com%2Fen-us%2Fazure%2Fhdinsight%2Fhadoop%2FTOC.jsonandbc=https%3A%2F%2Fdocs.microsoft.com% 2Fen-us%2Fazure%2Fbread%2Ftoc.json

• Question 72:

  You are designing an AI application that will use an azure Machine Learning Studio experiment.

  The source data contains more than 200 TB of relational tables. The experiment will run once a month. You need to identify a data storage solution for the application. The solution must minimize compute costs. Which data storage solution should you identify?

  A. Azure Database for MySQL

  B. Azure SQL Database

  C. Azure SQL Data Warehouse

  Correct Answer: B

  References: https://azure.microsoft.com/en-us/pricing/details/sql-database/single/

• Question 73:

  You design an AI workflow that combines data from multiple data sources for analysis. The data sources are composed of:

  1.

  JSON files uploaded to an Azure Storage account

  2.

  On-premises Oracle databases

  3.

  Azure SQL databases

  Which service should you use to ingest the data?

  A. Azure Data Factory

  B. Azure SQL Data Warehouse

  C. Azure Data Lake Storage

  D. Azure Databricks

  Correct Answer: A

  References: https://docs.microsoft.com/en-us/azure/data-factory/introduction

• Question 74:

  Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while

  others might not have a correct solution.

  After you answer a question, you will NOT be able to return to it. As a result, these questions will not appear in the review screen.

  You have an app named App1 that uses the Face API.

  App1 contains several PersonGroup objects.

  You discover that a PersonGroup object for an individual named Ben Smith cannot accept additional entries. The PersonGroup object for Ben Smith contains 10,000 entries.

  You need to ensure that additional entries can be added to the PersonGroup object for Ben Smith. The solution must ensure that Ben Smith can be identified by all the entries.

  Solution: You modify the custom time interval for the training phase of App1.

  Does this meet the goal?

  A. Yes

  B. No

  Correct Answer: B

  Instead, use a LargePersonGroup. 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.

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

• Question 75:

  Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while

  others might not have a correct solution.

  After you answer a question, you will NOT be able to return to it. As a result, these questions will not appear in the review screen.

  You have an app named App1 that uses the Face API.

  App1 contains several PersonGroup objects.

  You discover that a PersonGroup object for an individual named Ben Smith cannot accept additional entries. The PersonGroup object for Ben Smith contains 10,000 entries.

  You need to ensure that additional entries can be added to the PersonGroup object for Ben Smith. The solution must ensure that Ben Smith can be identified by all the entries.

  Solution: You create a second PersonGroup object for Ben Smith. Does this meet the goal?

  A. Yes

  B. No

  Correct Answer: B

  Instead, use a LargePersonGroup. 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.

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

• Question 76:

  Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while

  others might not have a correct solution.

  After you answer a question, you will NOT be able to return to it. As a result, these questions will not appear in the review screen.

  You have an app named App1 that uses the Face API.

  App1 contains several PersonGroup objects.

  You discover that a PersonGroup object for an individual named Ben Smith cannot accept additional entries. The PersonGroup object for Ben Smith contains 10,000 entries.

  You need to ensure that additional entries can be added to the PersonGroup object for Ben Smith. The solution must ensure that Ben Smith can be identified by all the entries.

  Solution: You migrate all the entries to the LargePersonGroup object for Ben Smith.

  Does this meet the goal?

  A. Yes

  B. No

  Correct Answer: A

  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.

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

• Question 77:

  Your company plans to develop a mobile app to provide meeting transcripts by using speech-to-text. Audio from the meetings will be streamed to provide real-time transcription.

  You need to recommend which task each meeting participant must perform to ensure that the transcripts of the meetings can identify all participants.

  Which task should you recommend?

  A. Record the meeting as an MP4.

  B. Create a voice signature.

  C. Sign up for Azure Speech Services.

  D. Sign up as a guest in Azure Active Directory (Azure AD)

  Correct Answer: B

  The first step is to create voice signatures for the conversation participants. Creating voice signatures is required for efficient speaker identification.

  Note: In addition to the standard baseline model used by the Speech Services, you can customize models to your needs with available data, to overcome speech recognition barriers such as speaking style, vocabulary and background noise.

  References:

  https://docs.microsoft.com/bs-latn-ba/azure/cognitive-services/speech-service/how-to-use-conversation-transcription-service

• Question 78:

  You need to create a prototype of a bot to demonstrate a user performing a task. The demonstration will use the Bot Framework Emulator. Which botbuilder CLI tool should you use to create the prototype?

  A. Chatdown

  B. QnAMaker

  C. Dispatch

  D. LuDown

  Correct Answer: A

  Use Chatdown to produce prototype mock conversations in markdown and convert the markdown to transcripts you can load and view in the new V4 Bot Framework Emulator. Incorrect Answers:

  B: QnA Maker is a cloud-based API service that lets you create a conversational question-and-answer layer over your existing data. Use it to build a knowledge base by extracting questions and answers from your semi-structured content, including FAQs, manuals, and documents. Answer users' questions with the best answers from the QnAs in your knowledge base--automatically. Your knowledge base gets smarter, too, as it continually learns from user behavior.

  C: Dispatch lets you build language models that allow you to dispatch between disparate components (such as QnA, LUIS and custom code).

  D: LuDown build LUIS language understanding models using markdown files

  References: https://github.com/microsoft/botframework/blob/master/README.md

• Question 79:

  You are designing an AI solution that will provide feedback to teachers who train students over the Internet. The students will be in classrooms located in remote areas. The solution will capture video and audio data of the students in the classrooms.

  You need to recommend Azure Cognitive Services for the AI solution to meet the following requirements:

  1.

  Alert teachers if a student facial expression indicates the student is angry or scared.

  2.

  Identify each student in the classrooms for attendance purposes.

  3.

  Allow the teachers to log voice conversations as text. Which Cognitive Services should you recommend?

  A. Face API and Text Analytics

  B. Computer Vision and Text Analytics

  C. QnA Maker and Computer Vision

  D. Speech to Text and Face API

  Correct Answer: D

  Speech-to-text from Azure Speech Services, also known as speech-to-text, enables real-time transcription of audio streams into text that your applications, tools, or devices can consume, display, and take action on as command input.

  Face detection: Detect one or more human faces in an image and get back face rectangles for where in the image the faces are, along with face attributes which contain machine learning-based predictions of facial features. The face attribute

  features available are: Age, Emotion, Gender, Pose, Smile, and Facial Hair along with 27 landmarks for each face in the image.

  References:

  https://docs.microsoft.com/en-us/azure/cognitive-services/speech-service/speech-to-text https://azure.microsoft.com/en-us/services/cognitive-services/face/

• Question 80:

  You need to evaluate trends in fuel prices during a period of 10 years. The solution must identify unusual fluctuations in prices and produce visual representations.

  Which Azure Cognitive Services API should you use?

  A. Anomaly Detector

  B. Computer Vision

  C. Text Analytics

  D. Bing Autosuggest

  Correct Answer: A

  The Anomaly Detector API enables you to monitor and detect abnormalities in your time series data with machine learning. The Anomaly Detector API adapts by automatically identifying and applying the best-fitting models to your data, regardless of industry, scenario, or data volume. Using your time series data, the API determines boundaries for anomaly detection, expected values, and which data points are anomalies.

  References: https://docs.microsoft.com/en-us/azure/cognitive-services/anomaly-detector/overview