The algorithm used to train a multi-layer neural network, computing the gradient of a loss function with respect to every weight in the network by applying the chain rule backward from the output layer, then using that gradient to adjust the weights.
Facts
Core PrincipleAn efficient application of the chain rule to neural networks, computing the gradient of the loss with respect to the network weights. 2 Connections
In Field
Invented
Geoffrey Hinton co-authored the 1986 Nature paper with David Rumelhart and Ronald Williams that popularized backpropagation for training multi-layer neural networks.
Sources
1. Wikipedia: Geoffrey Hinton
Wikimedia FoundationBackpropagation sectionQuote, Backpropagation section
With David Rumelhart and Ronald J. Williams, Hinton co-authored a highly cited paper published in 1986 that popularised the backpropagation algorithm for training multi-layer neural networks
2. Backpropagation, Wikipedia
OverviewQuote, Overview
It is an efficient application of the chain rule to neural networks.
Reader Challenges (0)
No disputes yet. Spotted an error or a better source? Open the first one.
Sign in to dispute this or suggest a correction.