Core Machine Learning Concepts

Explain the differences between supervised, unsupervised, and reinforcement learning with examples.

Describe the bias-variance tradeoff and its implications for model selection.

Define common evaluation metrics for classification tasks: accuracy, precision, recall, and F1-score.

Explain loss functions and how gradient descent minimizes them to optimize model parameters.

Describe overfitting and common regularization techniques used to mitigate it.

Describe the structure of a feedforward neural network, including layers, weights, biases, and activation functions.

Explain backpropagation at a conceptual level and its role in training neural networks.