Feedforward backpropagation artificial neural networks on reconfigurable meshes

The artificial neural networks (ANNs) have been used successfully in applic ations such as pattern recognition, image processing, automation and contro l. Majority of today's applications use backpropagate feedforward ANN. In t his paper, two methods of P pattern L layer ANN learning on n x n RMESH hav e been presented. One required memory space of O(nL) but conceptually is si mpler to develop and the other uses pipelined approach which reduces the me mory requirement to O(L). Both of these algorithms take O(PL) time and are optimal for RMESH architecture. (C) 1998 Elsevier Science B.V. All rights r eserved.