Rating is available when the video has been rented.
This feature is not available right now. Please try again later.
Uploaded on Jan 7, 2012
In this video we will derive the back-propagation algorithm as is used for neural networks. I use the sigmoid transfer function because it is the most common, but the derivation is the same, and easily extensible.
Helpful diagram: http://db.tt/B5Nyo14D This particular video goes from the derivative of the sigmoid itself to the delta for the output layer