What is regularization and name two examples.

• A. The process of reducing training data to speed up training.
• B. Techniques to increase model complexity.
• C. Techniques to decrease training time by early stopping.
• D. Techniques to reduce overfitting; examples include L1 (Lasso) and L2 (Ridge) regularization.

Answer: (D)

Regularization reduces overfitting by adding a penalty term to the loss that discourages the model from becoming too complex. This keeps the model weights smaller and the overall complexity in check, helping it generalize better to new data. Two common examples are L1 regularization, also known as Lasso, which adds the sum of the absolute values of the weights. This can drive some weights to zero, effectively performing feature selection and producing a sparser model. The other is L2 regularization, or Ridge, which adds the sum of the squares of the weights. This shrinks coefficients toward zero but usually keeps all features present, resulting in a more stable model. These penalties curb complexity to improve generalization. The other options describe different ideas—reducing data, increasing complexity, or a training-time tactic—not the penalty-based approach that defines regularization.