regularization
Everything on Ground Truth tagged “regularization” — 2 items.
Label smoothing: teaching a classifier not to be certain beyond the evidence Lesson
Label smoothing replaces a perfectly one-hot training target with a slightly softened probability distribution, discouraging a classifier from treating every labeled example as proof that all alternatives are impossible.
Data augmentation: teaching a model more without collecting more Lesson
Data augmentation multiplies a training set by transforming existing examples in ways that change the input but not the answer, teaching a model which differences to ignore -- and the choice of transformation encodes exactly what you want it to be blind to.