Artificial Intelligence Machine Learning Fundamentals 1 — Questions and Answers
Question 1: Which type of machine learning uses labeled training data to learn a mapping from inputs to outputs?
- Unsupervised learning
- Supervised learning (Correct answer)
- Reinforcement learning
- Semi-supervised learning
Correct answer: Supervised learning
Supervised learning trains on labeled input-output pairs to learn a predictive mapping.
Question 2: What is the term for a model that performs well on training data but poorly on new data?
- Underfitting
- Regularization
- Overfitting (Correct answer)
- Generalization
Correct answer: Overfitting
Overfitting occurs when a model memorizes training data instead of learning generalizable patterns.
Question 3: Which algorithm builds an ensemble of decision trees to improve prediction accuracy?
- Linear regression
- K-means clustering
- Random forest (Correct answer)
- Naive Bayes
Correct answer: Random forest
Random forest combines many decision trees, using bagging and feature randomness to reduce variance.
Question 4: What does the 'bias-variance tradeoff' describe in machine learning?
- The tradeoff between model speed and accuracy
- The balance between underfitting and overfitting (Correct answer)
- The tradeoff between training size and test size
- The balance between precision and recall
Correct answer: The balance between underfitting and overfitting
The bias-variance tradeoff describes the tension between a model's error from wrong assumptions (bias) and sensitivity to fluctuations in training data (variance).
Question 5: Which metric is most appropriate when false negatives are more costly than false positives?
- Precision
- Accuracy
- Recall (Correct answer)
- Specificity
Correct answer: Recall
Recall (sensitivity) measures the proportion of actual positives correctly identified, minimizing false negatives.
Question 6: What is k-fold cross-validation used for in machine learning?
- Selecting the number of clusters
- Estimating model performance on unseen data (Correct answer)
- Reducing dimensionality of features
- Normalizing input features
Correct answer: Estimating model performance on unseen data
K-fold cross-validation splits data into k folds, training and validating k times to get a reliable performance estimate.
Artificial Intelligence Machine Learning Fundamentals 1
Which type of machine learning uses labeled training data to learn a mapping from inputs to outputs?