deep-learning
The loss landscape as a search space
taught
Taught in
-
Training is a search for the lowest loss
Deep Learning / Neural Networks
Requires
- loss-function required
Required by
- Gradient descent: the update rule required
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.