AI For Beginners 2 — 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
- Self-supervised learning
Correct answer: Supervised learning
Supervised learning trains on labeled input-output pairs so the model can predict outputs for new inputs.
Question 2: What does the term 'overfitting' mean in machine learning?
- The model trains too slowly
- The model performs well on training data but poorly on new data (Correct answer)
- The model has too few parameters
- The model ignores the training data entirely
Correct answer: The model performs well on training data but poorly on new data
Overfitting occurs when a model memorizes training data noise and fails to generalize to unseen examples.
Question 3: What is a neural network's 'activation function' used for?
- To initialize model weights
- To introduce non-linearity into the network (Correct answer)
- To split data into batches
- To compute the loss value
Correct answer: To introduce non-linearity into the network
Activation functions add non-linearity, allowing neural networks to learn complex patterns beyond simple linear relationships.
Question 4: Which metric is most appropriate for evaluating a binary classification model on a heavily imbalanced dataset?
- Accuracy
- F1 Score (Correct answer)
- Mean Squared Error
- R-squared
Correct answer: F1 Score
F1 Score balances precision and recall, making it more informative than accuracy when class distribution is skewed.
Question 5: What is the purpose of a validation set during model training?
- To provide extra training samples
- To tune hyperparameters without touching the test set (Correct answer)
- To replace the need for a test set
- To store the final model weights
Correct answer: To tune hyperparameters without touching the test set
The validation set allows engineers to tune hyperparameters and detect overfitting before final evaluation on the test set.
Question 6: Which Python library is most commonly used for numerical array operations in AI/ML pipelines?
- Pandas
- NumPy (Correct answer)
- Matplotlib
- Scikit-learn
Correct answer: NumPy
NumPy provides fast multi-dimensional array operations that underpin nearly all scientific computing and ML frameworks.
Question 7: What does 'batch size' refer to in neural network training?
- The number of layers in the network
- The number of training samples processed before updating weights (Correct answer)
- The total size of the training dataset
- The number of epochs to train
Correct answer: The number of training samples processed before updating weights
Batch size controls how many samples are used to compute the gradient before each weight update step.
AI For Beginners 2
Which type of machine learning uses labeled training data to learn a mapping from inputs to outputs?