Microsoft Azure AI Fundamentals Flashcards
7 cards from real Microsoft Azure AI Fundamentals practice questions. Tap to flip, then mark Knew It or Still Learning — missed cards come back until you master them.
Read the first 7 Microsoft Azure AI Fundamentals flashcards as text
Which Azure service provides pre-built AI models for vision, speech, language, and decision-making through REST APIs?
Answer: Azure Cognitive Services
Azure Cognitive Services offers pre-built AI capabilities accessible via REST APIs without requiring ML expertise.
What is the primary purpose of Azure Bot Service?
Answer: To build, connect, and manage intelligent chatbots
Azure Bot Service provides an integrated environment for developing, deploying, and managing conversational AI bots.
In Azure Machine Learning, what is an 'experiment'?
Answer: A named grouping of training runs used to track metrics
An experiment in Azure ML is a named container that groups related runs, allowing you to compare metrics and outputs across training iterations.
Which type of machine learning problem would you use to predict whether an email is spam or not spam?
Answer: Binary classification
Spam detection is a binary classification problem because the output is one of two discrete categories: spam or not spam.
What does the 'Text Analytics' feature in Azure Cognitive Services help identify?
Answer: Sentiment, key phrases, and entities in text
Text Analytics can detect sentiment (positive/negative/neutral), extract key phrases, and identify named entities like people, places, and organizations.
Which principle of Responsible AI ensures that AI systems work correctly for all users regardless of demographic group?
Answer: Fairness
Fairness means AI systems should treat all people equitably and avoid biased outcomes based on characteristics like gender, race, or age.
What is 'feature engineering' in the context of machine learning?
Answer: Selecting and transforming raw data into inputs that improve model performance
Feature engineering involves selecting, transforming, and creating input variables from raw data to help the model learn patterns more effectively.