Title

Minimal Disturbance Back-Propagation Algorithm

Abstract

Summary form only given, as follows. A novel learning algorithm for multilayered neural networks is presented. This algorithm, called minimal disturbance backpropagation, approximates a least mean squared error minimization of the error function while minimally disturbing the connection weights in the network. This means that the information previously trained into the network is disturbed to the smallest amount possible while achieving the desired error correction. Simulation results indicate that this algorithm is more robust and yields much faster convergence rates than the standard backpropagation algorithm.

Publication Date

12-1-1989

Publication Title

IJCNN Int Jt Conf Neural Network

Number of Pages

625-

Document Type

Article; Proceedings Paper

Identifier

scopus

Socpus ID

0024879687 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/0024879687

This document is currently not available here.

Share

COinS