Data Skeptic

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.

Direct download: the-vanishing-gradient.mp3
Category:general -- posted at: 8:00am PDT

1