deep-learning
Weight decay
taught
Taught in
-
Weight decay: keeping weights small
Deep Learning / Neural Networks
Requires
- overfitting-and-underfitting required
-
l2-regularization
required
Weight decay in a network's training loop is L2 regularization applied to its parameters.
Required by
Nothing in the catalog needs this yet.
Local knowledge map
Local knowledge map
Click to expand
Solid arrows are required prerequisites; dashed are recommended or helpful. Lower rows are more foundational. Click any box to jump to that concept.