When a deep learning model shows low training loss but high validation loss on Exam 3 scenario 1, which intervention most directly targets overfitting?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — if train looks perfect and validation looks awful, you're memorizing. Regularize and check validation again.
Full explanation below image
Full Explanation
Overfitting is indicated by a train/validation gap. Regularization (dropout, weight decay, early stopping, augmentation) improves generalization. Increasing depth until zero train loss worsens memorization. Deleting validation hides the problem. Disabling shuffle can also harm generalization. Practitioners should track both curves and use a held-out test set only for final evaluation.