Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!sun-barr!apple!usc!samsung!uakari.primate.wisc.edu!crdgw1!greenba From: greenba@gambia.crd.ge.com (ben a green) Newsgroups: comp.ai.neural-nets Subject: Re: Backpropagation... What is it? Message-ID: Date: 13 Nov 90 16:58:37 GMT References: <7556@uwm.edu> <11574@hubcap.clemson.edu> Sender: news@crdgw1.crd.ge.com Organization: GE Corporate Research & Development Lines: 17 In-reply-to: svissag@hubcap.clemson.edu's message of 13 Nov 90 16:27:18 GMT Backpropagation is nothing more than the application of the chain rule of differentiation to the task of calculating the gradient with respect to weights and biases of a cost function for a layered, feedforward net. It's amazing that it took so many years after Minsky and Paepert's denunciation of the perceptron for people to think of BP as a solution to the training problem. (Maybe the discovery really was the use of differentiable node functions instead of flipflops, not backpropagation.) See _Parallel Distributed Processing_, vol. 1, chapter 8. It's a book by Rumelhart, McClelland, et al. from MIT Press, 1988. -- Ben A. Green, Jr. greenba@gambia.crd.ge.com "Nature abhors a physicist."