Microsoft Azure AI Fundamentals General 5 — Questions and Answers
Question 1: Which Azure service provides real-time translation of spoken conversations between languages?
- Azure AI Language
- Azure AI Speech with speech translation (Correct answer)
- Azure AI Translator text-only API
- Azure AI Vision
Correct answer: Azure AI Speech with speech translation
Azure AI Speech includes a speech translation feature that transcribes and translates spoken audio in real time across multiple languages.
Question 2: In the context of Azure OpenAI Service, what is a 'token'?
- An API authentication key
- A unit of text (word or word fragment) that the model processes (Correct answer)
- A deployment configuration setting
- A billing unit equal to one API call
Correct answer: A unit of text (word or word fragment) that the model processes
A token is the basic unit of text that language models process; English words are typically 1–2 tokens, and model usage and costs are measured in tokens consumed.
Question 3: Which responsible AI principle is most concerned with ensuring AI systems work correctly and safely across varying conditions?
- Fairness
- Inclusiveness
- Reliability and Safety (Correct answer)
- Accountability
Correct answer: Reliability and Safety
Reliability and Safety focuses on ensuring AI systems perform as intended, resist manipulation, and fail gracefully without causing harm across different conditions.
Question 4: What is the purpose of 'prompt engineering' when working with large language models?
- Optimizing the model's internal weights through fine-tuning
- Crafting effective input text to guide the model toward desired outputs (Correct answer)
- Reducing the number of parameters in a model
- Monitoring model performance in production
Correct answer: Crafting effective input text to guide the model toward desired outputs
Prompt engineering is the practice of designing and refining the text inputs given to a language model to elicit accurate, relevant, and useful responses.
Question 5: A hospital wants to predict which patients are at high risk of readmission within 30 days of discharge. Which type of ML task is this?
- Clustering
- Binary classification (Correct answer)
- Regression
- Object detection
Correct answer: Binary classification
Predicting whether a patient will or will not be readmitted is a binary classification task with two possible outcome classes: readmitted or not readmitted.
Question 6: Which Azure Machine Learning capability automates the process of selecting algorithms and tuning hyperparameters?
- Azure ML Pipelines
- Automated ML (AutoML) (Correct answer)
- Azure ML Designer
- Model Registry
Correct answer: Automated ML (AutoML)
AutoML in Azure Machine Learning automatically iterates through multiple algorithms and hyperparameter combinations to find the best-performing model for a given dataset.
Question 7: What distinguishes 'deep learning' from traditional machine learning?
- Deep learning requires no data to train
- Deep learning uses multi-layered neural networks to automatically learn hierarchical feature representations (Correct answer)
- Deep learning only works on structured tabular data
- Deep learning models are always smaller and faster than traditional models
Correct answer: Deep learning uses multi-layered neural networks to automatically learn hierarchical feature representations
Deep learning uses neural networks with many layers that automatically learn hierarchical feature representations from raw data, eliminating the need for manual feature engineering.
Microsoft Azure AI Fundamentals General 5
Which Azure service provides real-time translation of spoken conversations between languages?