Microsoft AI-900 Online Practice Questions and Exam Preparation

Microsoft AI-900 Online Questions & Answers

• Question 311:

  You have an AI solution that provides users with the ability to control smart devices by using verbal commands.

  Which two types of natural language processing (NLP) workloads does the solution use? Each correct answer presents part of the solution.

  NOTE: Each correct selection is worth one point.

  A. text-to-speech
  B. key phrase extraction
  C. speech-to-text
  D. language modeling
  E. translation
  C. speech-to-text
  D. language modeling

  ---

  Explanation

  This should be speech-to-text and language modeling. You need to use language modeling to determine the intent of the utterance and to perform an action based on that intent.

• Question 312:

  DRAG DROP

  Match the Azure Al service to the appropriate generative Al capability.

  To answer, drag the appropriate service from the column on the left to its capability on the right. Each service may be used once, more than once, or not at all.

  NOTE: Each correct match is worth one point.

  Select and Place:

  

  

• Question 313:

  You plan to build a conversational AI solution that can be surfaced in Microsoft Teams, Microsoft Cortana, and Amazon Alexa.

  Which service should you use?

  A. Azure Bot Service
  B. Azure Cognitive Search
  C. Speech
  D. Language service
  A. Azure Bot Service

  ---

  Explanation

  Build an enterprise-grade conversational bot This reference architecture describes how to build an enterprise-grade conversational bot (chatbot) using the Azure Bot Framework.

  Authentication. Users start by authenticating themselves using whatever mechanism is provided by their channel of communication with the bot. The bot framework supports many communication channels, including Cortana, Microsoft Teams, Facebook Messenger, Kik, and Slack.

• Question 314:

  HOTSPOT

  For each of the following statements, select Yes if the statement is true. Otherwise, select No.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  References:

  https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/get-started-build-detector

• Question 315:

  Which action can be performed by using the Azure Al Vision service?

  A. identifying breeds of animals in live video streams
  B. extracting key phrases from documents
  C. extracting data from handwritten letters
  D. creating thumbnails for training videos
  D. creating thumbnails for training videos

• Question 316:

  In which two scenarios can you use the Form Recognizer service? Each correct answer presents a complete solution.

  NOTE: Each correct selection is worth one point.

  A. Identify the retailer from a receipt
  B. Translate from French to English
  C. Extract the invoice number from an invoice
  D. Find images of products in a catalog
  A. Identify the retailer from a receipt
  C. Extract the invoice number from an invoice

  ---

  Explanation

  References:

  https://docs.microsoft.com/en-us/azure/applied-ai-services/form-recognizer/overview?tabs=v2-1

• Question 317:

  Which two scenarios are examples of a conversational AI workload? Each correct answer presents a complete solution.

  NOTE: Each correct selection is worth one point.

  A. a smart device in the home that responds to questions such as "What will the weather be like today?"
  B. a website that uses a knowledge base to interactively respond to users' questions
  C. assembly line machinery that autonomously inserts headlamps into cars
  D. monitoring the temperature of machinery to turn on a fan when the temperature reaches a specific threshold
  A. a smart device in the home that responds to questions such as "What will the weather be like today?"
  B. a website that uses a knowledge base to interactively respond to users' questions

  ---

  Explanation

  Natural language processing (NLP) is used for tasks such as sentiment analysis, topic detection, language detection, key phrase extraction, and document categorization.

  References:

  https://docs.microsoft.com/en-us/azure/architecture/data-guide/technology-choices/natural-language-processing

• Question 318:

  You need to build a system that translates text between multiple languages in real time.

  Which service should you use?

  A. Text Analytics
  B. Translator
  C. Speech
  D. QnA Maker
  B. Translator

  ---

  Explanation

  The Translator service provides real-time multilingual text translation using neural machine translation technology.

• Question 319:

  HOTSPOT

  Select the answer that correctly completes the sentence.

  

  

  ---

  The Azure OpenAI Service provides access to advanced Generative Pre-trained Transformer (GPT) models developed by OpenAI, such as GPT-3, GPT-3.5, and GPT-4. These models are capable of performing a wide range of natural language processing (NLP) and generative AI tasks - including text completion, summarization, translation, question answering, content creation, and code generation. According to the Microsoft Azure AI Fundamentals (AI-900) study guide and Microsoft Learn documentation for Azure OpenAI, this managed service allows developers to deploy and integrate GPT-based models within their own applications using REST APIs or the Azure SDK. The service handles scalability, performance, and infrastructure automatically, meaning users do not need to manage servers or computational resources manually. Option review: Supports the deployment of GPT-based models - # Correct. Azure OpenAI is specifically

  designed for deploying and operationalizing GPT models and similar transformer-based architectures. Provides capabilities exclusively for vision-related tasks - # Incorrect. Vision tasks (like image classification or object detection) are part of Azure AI Vision. Provides capabilities exclusively for speech-related tasks - # Incorrect. Speech processing (speech-to-text, text-to-speech, translation) belongs to Azure AI Speech Services, not Azure OpenAI. Requires manual infrastructure

  management for scalability - # Incorrect. Azure OpenAI is a fully managed service; scalability and performance are handled automatically by Azure. Therefore, the correct completion of the sentence is:

  "Azure OpenAI Service supports the deployment of GPT-based models."

• Question 320:

  Which metric is commonly used to evaluate a classification model?

  A. root mean squared error (RMSE)
  B. coefficient of determination (R2)
  C. accuracy
  D. mean absolute error (MAE)
  C. accuracy

  ---

  Explanation

  Accuracy measures the proportion of correct predictions made by a classification model. RMSE, MAE, and R2 are used for regression models.