An ML specialist’s deep-learning sentiment model trained on movie reviews exhibits overfitting after validation. Which actions will most improve generalization and reduce overfitting? (Choose three.)

Overfitting occurs when a model learns the training data too well, including noise, and performs poorly on unseen data. L1 and L2 regularization (weight decay) penalize large weights, encouraging simpler models and preventing reliance on specific features. Dropout regularization randomly deactivates neurons during training, forcing the network to learn more robust features and preventing co-adaptation of neurons. Reducing the number of layers simplifies the model architecture, decreasing its capacity to memorize the training data and improving generalization. Shuffling the dataset with a different random seed is good practice but doesn't directly address overfitting. Reducing the learning rate helps with convergence but not necessarily overfitting. Adding more layers increases model complexity, which would worsen overfitting.