Microsoft AI-900 Online Practice Questions and Exam Preparation

Microsoft AI-900 Online Questions & Answers

• Question 271:

  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.

  

  

  ---

  Box 1: Yes

  Image classification is a popular area of artificial intelligence. One application of image classification that's already being used in industry is the detection of quality issues on assembly lines during manufacturing. In a typical production line, components travel down the assembly line from one station to another, at the end of which an inspector steps in to look for problems-a manual and error-prone process. AI-driven image classification reduces human effort and automatically classifies images as pass or fail. This improves not only the efficiency of the human operators in the validation process, but also the quality of the overall manufacturing process.

  Box 2: Yes

  Object detection is similar to tagging, but the API returns the bounding box coordinates (in pixels) for each object found in the image. For example, if an image contains a dog, cat and person, the Detect operation will list those objects with their coordinates in the image. You can use this functionality to process the relationships between the objects in an image. It also lets you determine whether there are multiple instances of the same object in an image.

  Box 3: No

  References:

  https://azure.microsoft.com/en-us/use-cases/defect-detection-with-image-analysis/https://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/concept-object-detection

• Question 272:

  You need to ensure that an AI system does not favor any specific demographic group unfairly.

  Which responsible AI principle should you prioritize?

  A. transparency
  B. fairness
  C. inclusiveness
  D. accountability
  B. fairness

  ---

  Explanation

  Fairness ensures that AI systems treat all individuals and groups equitably, avoiding bias and discrimination in outcomes.

• Question 273:

  HOTSPOT

  Select the answer that correctly completes the sentence.

  

  

  ---

  According to the Microsoft Azure AI Fundamentals (AI-900) official study guide and Microsoft Learn module "Identify features of common machine learning types", regression is a supervised machine learning technique used to predict continuous numerical values based on one or more input features. In this scenario, the task is to predict a vehicle's miles per gallon (MPG)-a continuous numeric value-based on several measurable factors such as weight, engine power, and other specifications. Regression models learn the mathematical relationship between input variables (independent features) and a numeric target variable (dependent outcome). Common regression algorithms include linear regression, decision tree regression, and support vector regression. In the example, the model would analyze historical data of vehicles and learn patterns that map characteristics (like engine size, horsepower, and weight) to fuel efficiency. Once trained, it can predict the MPG for a new vehicle configuration. The other options describe different problem types: Classification predicts discrete categories (for example, whether a car is "fuel efficient" or "not fuel efficient"), not continuous values.

  Clustering is an unsupervised learning method that groups data points based on similarities without predefined labels, not predictive modeling. Anomaly detection identifies data points that significantly deviate from normal patterns, such as detecting engine sensor failures or fraudulent transactions. Since predicting MPG involves estimating a numeric value within a continuous range, regression is the most appropriate model type. In summary, per AI-900 training content, regression models are used when the output variable is numeric, classification for categorical outputs, and clustering for pattern discovery. Therefore, predicting miles per gallon based on vehicle features is a textbook example of a regression problem in Azure Machine Learning.

• Question 274:

  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.

  

  

• Question 275:

  An app that analyzes social media posts to identify their tone is an example of which type of natural language processing (NLP) workload?

  A. sentiment analysis
  B. speech recognition
  C. key phrase extraction
  D. entity recognition
  A. sentiment analysis

  ---

  Explanation

  Sentiment analysis is analytical technique that uses statistics, natural language processing, and machine learning to determine the emotional meaning of communications. Companies use sentiment analysis to evaluate customer messages, call center interactions, online reviews, social media posts, and other content.

  References:

  https://www.cio.com/article/189218/what-is-sentiment-analysis-using-nlp-and-ml-to-extract-meaning.html

• Question 276:

  Which natural language processing feature can be used to identify the main talking points in customer feedback surveys?

  A. language detection
  B. translation
  C. entity recognition
  D. key phrase extraction
  D. key phrase extraction

• Question 277:

  You have a website that includes customer reviews.

  You need to store the reviews in English and present the reviews to users in their respective language by recognizing each user's geographical location.

  Which type of natural language processing workload should you use?

  A. key phrase extraction
  B. speech recognition
  C. language modeling
  D. translation
  A. key phrase extraction

• Question 278:

  HOTSPOT

  You have the following dataset.

  

  You plan to use the dataset to train a model that will predict the house price categories of houses.

  What are Household Income and House Price Category? To answer, select the appropriate option in the answer area.

  NOTE: Each correct selection is worth one point.

  

  

  ---

  References:

  https://docs.microsoft.com/en-us/azure/machine-learning/studio/interpret-model-results

• Question 279:

  You use drones to identify where weeds grow between rows of crops to send an instruction for the removal of the weeds.

  This is an example of which type of computer vision?

  A. object detection
  B. optical character recognition (OCR)
  C. scene segmentation
  A. object detection

  ---

  Explanation

  Object detection is similar to tagging, but the API returns the bounding box coordinates for each tag applied. For example, if an image contains a dog, cat and person, the Detect operation will list those objects together with their coordinates in the image.

  Incorrect Answers:

  B: Optical character recognition (OCR) allows you to extract printed or handwritten text from images and documents.

  C: Scene segmentation determines when a scene changes in video based on visual cues. A scene depicts a single event and it's composed by a series of consecutive shots, which are semantically related.

  References:

  https://docs.microsoft.com/en-us/ai-builder/object-detection-overviewhttps://docs.microsoft.com/en-us/azure/cognitive-services/computer-vision/overview-ocrhttps://docs.microsoft.com/en-us/azure/azure-video-analyzer/video-analyzer-for-media-docs/video-indexer-overview

• Question 280:

  When training a model, why should you randomly split the rows into separate subsets?

  A. to train the model twice to attain better accuracy
  B. to train multiple models simultaneously to attain better performance
  C. to test the model by using data that was not used to train the model
  C. to test the model by using data that was not used to train the model

  ---

  Explanation

  The goal is to produce a trained (fitted) model that generalizes well to new, unknown data. The fitted model is evaluated using "new" examples from the held-out datasets (validation and test datasets) to estimate the model's accuracy in classifying new data.

  https://en.wikipedia.org/wiki/Training,_validation,_and_test_sets#:~:text=Training%20dataset,-A%20training%20dataset&text=The%20goal%20is%20to%20produce,accuracy%20in%20classifying%20new%20data.