Example Concept: Regularization techniques, such as L1 (Lasso) and L2 (Ridge) regularization, add a penalty term to the loss function of a model. This penalty discourages overly complex models by either shrinking the coefficients of less important features (L1) or reducing the overall magnitude of coefficients (L2). By controlling the complexity, regularization helps the model generalize better to new data, thus improving predictive performance on unseen datasets.