Example Concept: Regularization techniques like L1 and L2 add a penalty to the loss function based on the magnitude of the model weights, discouraging overly complex models. Dropout randomly deactivates a fraction of neurons during training, which helps prevent the model from becoming too reliant on any single feature. Data augmentation artificially increases the size of the training dataset by applying transformations like rotation, scaling, and flipping, which helps the model generalize better to unseen data.