Microsoft Azure AI Fundamentals Microsoft Azure AI Fundamentals MCQ 5 — Questions and Answers
Question 1: Which Azure AI service can analyze video content to extract insights such as scene detection, speaker identification, and transcript generation?
- Azure Computer Vision
- Azure Video Indexer (Correct answer)
- Azure Media Services
- Azure Stream Analytics
Correct answer: Azure Video Indexer
Azure Video Indexer uses AI to automatically extract rich insights from video, including transcripts, faces, emotions, topics, and scene changes.
Question 2: What is 'data drift' in the context of deployed machine learning models?
- Accidentally deleting training data
- Changes in input data distribution over time that degrade model performance (Correct answer)
- Gradual increase in model training time
- Unauthorized access to training datasets
Correct answer: Changes in input data distribution over time that degrade model performance
Data drift occurs when the statistical properties of production data change over time compared to the training data, causing model accuracy to decline.
Question 3: Which of the following best describes 'natural language generation' (NLG)?
- Converting spoken audio into written text
- Converting structured data or prompts into human-readable text (Correct answer)
- Analyzing the meaning and intent behind text
- Translating text from one language to another
Correct answer: Converting structured data or prompts into human-readable text
NLG is the AI capability of producing coherent, human-readable text from structured data, templates, or learned patterns.
Question 4: In Azure Machine Learning, what is a 'pipeline'?
- A network connection between Azure services
- A reusable workflow of ML steps such as data prep, training, and evaluation (Correct answer)
- A deployment configuration for ML models
- A monitoring dashboard for model performance
Correct answer: A reusable workflow of ML steps such as data prep, training, and evaluation
An Azure ML pipeline is a reusable, automated sequence of steps that defines and orchestrates an end-to-end machine learning workflow.
Question 5: Which responsible AI principle is most directly concerned with preventing AI systems from producing biased outcomes against specific demographic groups?
- Reliability
- Fairness (Correct answer)
- Privacy
- Inclusiveness
Correct answer: Fairness
Fairness requires that AI systems treat all individuals and groups equitably and do not produce discriminatory outcomes based on characteristics like race or gender.
Question 6: What type of AI task is performed when an Azure service listens to spoken words and converts them into written text?
- Text-to-speech synthesis
- Speech-to-text transcription (Correct answer)
- Intent recognition
- Language translation
Correct answer: Speech-to-text transcription
Speech-to-text (also called automatic speech recognition or ASR) converts spoken audio input into written text output.
Question 7: Which Azure Machine Learning feature helps explain why a model made a specific prediction by showing feature importance?
- AutoML
- Hyperdrive
- Model Interpretability / Explainability (Correct answer)
- Data Labeling
Correct answer: Model Interpretability / Explainability
Azure ML's model interpretability tools, including SHAP and LIME-based explanations, reveal which input features most influenced a specific prediction.
Microsoft Azure AI Fundamentals Microsoft Azure AI Fundamentals MCQ 5
Which Azure AI service can analyze video content to extract insights such as scene detection, speaker identification, and transcript generation?