AI summary

This paper introduces an adaptive neural network with asymmetric connections, generalizing the back-propagation algorithm to recurrent neural networks, and demonstrating its architectural simplicity compared to existing master/slave networks.

Abstract

An adaptive neural network with asymmetric connections is introduced. This network is related to the Hopfield network with graded neurons and uses a recurrent generalization of the 8 rule of Rumelhart, Hinton, and Williams to modify adaptively the synaptic weights. The new network bears a resemblance to the master/slave network of Lapedes and Farber, but it is architecturally simpler.