D

Dropout

Tool / ProductMentioned in 1 video

Regularization technique used in the scaled-up model to reduce overfitting (randomly disables activations during training).

Videos Mentioning Dropout

Let's build GPT: from scratch, in code, spelled out.

Let's build GPT: from scratch, in code, spelled out.

Andrej Karpathy

Regularization technique used in the scaled-up model to reduce overfitting (randomly disables activations during training).