Learning on a General Network

Part of Neural Information Processing Systems 0 (NIPS 1987)

Bibtex Metadata Paper

Authors

Amir Atiya

Abstract

This paper generalizes the backpropagation method to a general network containing feed(cid:173)

back t;onnections. The network model considered consists of interconnected groups of neurons, where each group could be fully interconnected (it could have feedback connections, with pos(cid:173) sibly asymmetric weights), but no loops between the groups are allowed. A stochastic descent algorithm is applied, under a certain inequality constraint on each intra-group weight matrix which ensures for the network to possess a unique equilibrium state for every input.