Data Skeptic

[MINI] The Vanishing Gradient

15 min • 30 juni 2017

This episode discusses the vanishing gradient - a problem that arises when training deep neural networks in which nearly all the gradients are very close to zero by the time back-propagation has reached the first hidden layer. This makes learning virtually impossible without some clever trick or improved methodology to help earlier layers begin to learn.

Senaste avsnitt

Podcastbild

00:00 -00:00
00:00 -00:00