Vanishing Gradient

AI and Machine Learning · Training and Optimisation · vanishing-gradient.yaml

Repeated multiplication by factors below one drives the gradient toward zero as it travels back through layers or time steps, so early parameters stop moving.

Colour is the family; a dashed line is the second member of it.

Drag to pan · scroll to zoom · click a node to open it
G backpropagation Backpropagation vanishing-gradient Vanishing Gradient vanishing-gradient->backpropagation

This node

References