Microsoft AI-900 Online Practice Questions and Exam Preparation

Microsoft AI-900 Online Questions & Answers

• Question 251:

  Which metric can you use to evaluate a classification model?

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

  ---

  Explanation

  What does a good model look like?

  An ROC curve that approaches the top left corner with 100% true positive rate and 0% false positive rate will be the best model. A random model would display as a flat line from the bottom left to the top right corner. Worse than random would dip below the y=x line.

  References:

  https://docs.microsoft.com/en-us/azure/machine-learning/how-to-understand-automated-ml#classification

• Question 252:

  You need to generate cartoons for use in a brochure. Each cartoon will be based on a text description.

  Which Azure OpenAI model should you use?

  A. Codex
  B. DALL-E
  C. GPT-3.5
  D. GPT-4
  B. DALL-E

• Question 253:

  HOTSPOT

  Select the answer that correctly completes the sentence.

  

  

  ---

  In Azure OpenAI Service, the temperature parameter directly controls the creativity and determinism of responses generated by models such as GPT-3.5. According to the Microsoft Learn documentation for Azure OpenAI models, temperature is a numeric value (typically between 0.0 and 2.0) that determines how "random" or "deterministic" the output should be. A lower temperature value (for example, 0 or 0.2) makes the model's responses more deterministic, meaning the same prompt consistently produces nearly identical outputs. A higher temperature value (for example, 0.8 or 1.0) encourages creativity and variety, causing the model to generate different phrasing or interpretations each time it responds. When a question specifies the need for more deterministic responses, Microsoft's guidance is to decrease the temperature parameter. This adjustment makes the model focus on the most probable tokens (words) rather than exploring less likely options, improving reliability and consistency-ideal for business or technical applications where consistent answers are essential. The other parameters serve different purposes: Frequency penalty reduces repetition of the same phrases but does not control randomness. Max response (max tokens) limits the maximum length of the generated output. Stop sequence defines specific tokens that tell the model when to stop generating text. Thus, the correct and Microsoft-verified completion is: "You can modify the Temperature parameter to produce more deterministic responses from a chat solution that uses the Azure OpenAI GPT-3.5 model."

• Question 254:

  body={text="polar bear standing on the ground", size="1024x1024"}

  Which Azure AI model should be used?

  A. Codex
  B. DALL-E
  C. GPT-4
  D. Azure OpenAI text completion model
  B. DALL-E

  ---

  Explanation

  DALL-E is an image generation model available through Azure OpenAI that creates images from text prompts. Parameters such as image size and prompt text are commonly used when generating images. Codex is designed for code generation and GPT-4 primarily focuses on text-based tasks.

• Question 255:

  HOTSPOT

  Select the answer that correctly completes the sentence.

  

  

  ---

  Clustering. According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn module "Identify features of common machine learning types", clustering is an unsupervised machine learning technique used to group data points into distinct segments or clusters based on shared characteristics. Unlike supervised learning (classification or regression), clustering works with unlabeled data, discovering natural groupings without predefined outcomes. In this question, Recency, Frequency, and Monetary (RFM) values are common marketing metrics used to evaluate customer behavior: Recency

  - how recently a customer made a purchase. Frequency - how often they make purchases. Monetary - how much money they spend. Using RFM analysis, a company can segment its customers into groups such as "loyal," "occasional," or "at-risk" buyers. This segmentation process does not rely on predefined labels but rather discovers patterns within the data - which is the defining characteristic of clustering. In the AI-900 context, clustering is described as a method that "groups items with similar features so that items in the same group are more similar to each other than to those in other groups." Common algorithms used include K-Means, Hierarchical Clustering, and DBSCAN, all available within Azure Machine Learning Designer and other Azure ML environments. To clarify the incorrect options: Classification is supervised learning used to predict discrete categories (e.g., yes/no, spam/not spam). Regression predicts continuous numeric values (e.g., house prices). Regularization is a model optimization technique, not a type of machine learning. Therefore, when businesses use RFM values to identify customer segments without labeled outcomes, this is an application of unsupervised learning through clustering.

• Question 256:

  A developer builds a chatbot powered by Azure OpenAI and wants it to interact with external tools such as search services and APIs.

  Which component enables the AI system to coordinate these interactions?

  A. AI agents
  B. Speech recognition models
  C. Image classification models
  D. Data labeling tools
  A. AI agents

  ---

  Explanation

  AI agents allow generative AI systems to perform tasks such as calling external tools, retrieving data, and coordinating responses. They enable the AI to act on behalf of users and interact with other services.

• Question 257:

  You have the process shown in the following exhibit.

  

  Which type AI solution is shown in the diagram?

  A. a sentiment analysis solution
  B. a chatbot
  C. a machine learning model
  D. a computer vision application
  B. a chatbot

• Question 258:

  DRAG DROP

  Match the Al workload to the appropriate task.

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

  NOTE: Each correct match is worth one point.

  Select and Place:

  

  

  ---

  This question tests your understanding of AI workloads as described in the Microsoft Azure AI Fundamentals (AI-900) study guide. Each Azure AI workload is designed to handle specific types of data and tasks: text, images, documents, or content generation.

  Extract data from medical admission forms for import into a patient tracking database # Azure AI Document IntelligenceFormerly known as Form Recognizer, this service belongs to the Azure AI Document Intelligence workload. It extracts key-value pairs, tables, and textual information from structured and semi-structured documents such as forms, invoices, and admission sheets. For medical forms, Document Intelligence can identify fields like patient name, admission date, and diagnosis and export them into structured formats for database import.

  Automatically create drafts for a monthly newsletter # Generative AIThis task involves creating original written content, which is a capability of Generative AI. Microsoft's Azure OpenAI Service uses large language models (like GPT-4) to generate human-like text, summaries, or articles. Generative AI workloads are ideal for automating creative writing, drafting newsletters, producing blogs, or summarizing reports.

  Analyze aerial photos to identify flooded areas # Computer VisionComputer Vision workloads involve analyzing and interpreting visual data from images or videos. This includes detecting objects, classifying scenes, and identifying patterns such as flooded regions in aerial imagery. Azure's Computer Vision or Custom Vision services can be trained to detect water coverage or terrain changes using image recognition techniques. Thus, the correct matches are: Azure AI Document Intelligence # Extract medical form data Generative AI # Create newsletter drafts Computer Vision # Identify flooded areas from aerial photos

• Question 259:

  You are designing an AI system that empowers everyone, including people who have hearing, visual, and other impairments.

  This is an example of which Microsoft guiding principle for responsible AI?

  A. fairness
  B. inclusiveness
  C. reliability and safety
  D. accountability
  B. inclusiveness

  ---

  Explanation

  Inclusiveness: At Microsoft, we firmly believe everyone should benefit from intelligent technology, meaning it must incorporate and address a broad range of human needs and experiences. For the 1 billion people with disabilities around the world, AI technologies can be a game-changer.

  References:

  https://docs.microsoft.com/en-us/learn/modules/responsible-ai-principles/4-guiding-principles

• Question 260:

  You are building an AI solution that must ensure decisions made by the system can be clearly understood by users and auditors.

  Which Microsoft responsible AI principle does this represent?

  A. fairness
  B. transparency
  C. inclusiveness
  D. reliability and safety
  B. transparency

  ---

  Explanation

  Transparency requires that AI systems be understandable and that stakeholders can interpret how decisions are made. This includes documenting models, data sources, and logic so that outcomes can be explained and audited.