Microsoft Azure AI Fundamentals General 3 — Questions and Answers
Question 1: Which Azure service would you use to extract key phrases and sentiment from customer reviews at scale?
- Azure AI Vision
- Azure AI Language (Correct answer)
- Azure AI Speech
- Azure AI Personalizer
Correct answer: Azure AI Language
Azure AI Language provides sentiment analysis and key phrase extraction capabilities to process and understand large volumes of text such as customer reviews.
Question 2: What is a 'confusion matrix' used for in machine learning?
- Visualizing neural network layer weights
- Summarizing the performance of a classification model across all classes (Correct answer)
- Displaying training loss over epochs
- Mapping input features to output labels
Correct answer: Summarizing the performance of a classification model across all classes
A confusion matrix summarizes classification model performance by showing true positives, true negatives, false positives, and false negatives for each class.
Question 3: In Azure Machine Learning, what is the role of a 'compute cluster'?
- Storing trained model artifacts
- Providing scalable compute resources for training and batch inference jobs (Correct answer)
- Managing API keys for deployed models
- Monitoring data drift in production
Correct answer: Providing scalable compute resources for training and batch inference jobs
A compute cluster in Azure Machine Learning is a scalable set of nodes used to run training experiments, hyperparameter tuning, and batch scoring workloads.
Question 4: Which principle of responsible AI ensures that AI systems can be examined and their decisions understood?
- Fairness
- Reliability
- Transparency (Correct answer)
- Privacy
Correct answer: Transparency
Transparency means AI systems and their decision-making processes should be understandable and explainable to developers, operators, and affected users.
Question 5: What type of machine learning involves an agent learning by receiving rewards or penalties for actions taken in an environment?
- Supervised learning
- Unsupervised learning
- Semi-supervised learning
- Reinforcement learning (Correct answer)
Correct answer: Reinforcement learning
Reinforcement learning trains an agent by rewarding desired behaviors and penalizing undesired ones as it interacts with an environment to maximize cumulative reward.
Question 6: Which Azure AI service can convert spoken audio into structured text transcripts?
- Azure AI Language
- Azure AI Translator
- Azure AI Speech (Correct answer)
- Azure AI Vision
Correct answer: Azure AI Speech
Azure AI Speech includes a speech-to-text capability that transcribes spoken audio into written text in real time or from recorded files.
Question 7: A retail company wants to recommend products to users based on purchase history. Which AI technique is most applicable?
- Anomaly detection
- Collaborative filtering (recommendation system) (Correct answer)
- Object detection
- Named entity recognition
Correct answer: Collaborative filtering (recommendation system)
Collaborative filtering is the core technique behind recommendation systems, identifying patterns in user behavior and purchase history to suggest relevant products.
Microsoft Azure AI Fundamentals General 3
Which Azure service would you use to extract key phrases and sentiment from customer reviews at scale?