deep-learning
Xavier and He initialization
taught
Taught in
-
Why all weights cannot start equal
Deep Learning / Neural Networks
-
Choosing the starting weights: Xavier and He
Deep Learning / Neural Networks
Requires
- vanishing-exploding-gradients required
Required by
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.