ConceptAI & ML
Weight initialization
The method of setting initial network weights to prevent activations from vanishing or exploding during training.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
2Each in their own terms, from the easiest level.
Yaser Abu-Mostafa
Initializing weights to random values instead of zero to break symmetry and allow the backpropagation algorithm to update weights effectively.
Lectures that assume it
2Connections
10The lectures that define it or assume it, and the concepts next to it.