deep-learning
nn.MSELoss, nn.BCELoss, and nn.CrossEntropyLoss
taught
Taught in
-
Losses are Chapter 7
Deep Learning / Neural Networks
Requires
- mean-squared-error required
- binary-cross-entropy required
-
categorical-cross-entropy
required
nn.CrossEntropyLoss applies softmax internally and needs Chapter 7's own logits-vs-probabilities distinction stated precisely.
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.