Microsoft Azure AI Fundamentals Machine Learning 2 — Questions and Answers
Question 1: Which Azure ML feature automatically selects the best algorithm and hyperparameters for a given dataset?
- Azure ML Pipelines
- Automated ML (AutoML) (Correct answer)
- Azure ML Designer
- Azure Databricks
Correct answer: Automated ML (AutoML)
Automated ML (AutoML) in Azure Machine Learning iterates over multiple algorithms and hyperparameter settings to automatically find the best model for your data.
Question 2: In supervised learning, what is the term for the variable the model is trained to predict?
- Feature
- Label (Correct answer)
- Parameter
- Hyperparameter
Correct answer: Label
In supervised learning, the label (also called the target) is the known value the model learns to predict from input features.
Question 3: Which type of machine learning is used when training data has no predefined correct answers?
- Supervised learning
- Reinforcement learning
- Unsupervised learning (Correct answer)
- Transfer learning
Correct answer: Unsupervised learning
Unsupervised learning finds patterns in data without labeled examples, such as grouping customers by purchasing behavior using clustering.
Question 4: What metric would you primarily use to evaluate a binary classification model's ability to avoid false positives?
- Recall
- Precision (Correct answer)
- RMSE
- R-squared
Correct answer: Precision
Precision measures the proportion of positive predictions that are actually correct, directly reflecting the model's ability to minimize false positives.
Question 5: In Azure Machine Learning, what is an 'endpoint' used for after model training?
- Storing training datasets
- Deploying the model for real-time or batch inference (Correct answer)
- Monitoring training runs
- Version-controlling experiments
Correct answer: Deploying the model for real-time or batch inference
An endpoint in Azure ML exposes a trained model as a web service so applications can send data and receive predictions in real time or via batch.
Question 6: Which Azure service is purpose-built for large-scale machine learning experimentation and MLOps?
- Azure Cognitive Services
- Azure Machine Learning (Correct answer)
- Azure Logic Apps
- Azure Data Factory
Correct answer: Azure Machine Learning
Azure Machine Learning is Microsoft's end-to-end platform for building, training, deploying, and managing ML models at scale with MLOps capabilities.
Question 7: What is 'overfitting' in a machine learning model?
- The model performs poorly on both training and test data
- The model learns the training data too well and performs poorly on new data (Correct answer)
- The model is trained on too little data
- The model takes too long to train
Correct answer: The model learns the training data too well and performs poorly on new data
Overfitting occurs when a model memorizes training data noise and specifics, causing high accuracy on training data but poor generalization to unseen data.
Microsoft Azure AI Fundamentals Machine Learning 2
Which Azure ML feature automatically selects the best algorithm and hyperparameters for a given dataset?