A Fast Procedure for Retraining the Multilayer Perceptron

C. M. Bishop

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper we describe a fast procedure for re-training a feed-forward network, previously trained by error back-propagation, following a small change in the training data. This technique would permit fine calibration of individual neural network based control systems in a mass-production environment. We also derive a generalised error back-propagation algorithm which allows an exact evaluation of all of the terms in the Hessian matrix. The fast re-training procedure is illustrated using a simple example.

Original languageEnglish
Pages (from-to)229–236
Number of pages8
JournalInternational Journal of Neural Systems
Volume2
Issue number3
DOIs
Publication statusPublished - 1 Jan 1991

Fingerprint

Dive into the research topics of 'A Fast Procedure for Retraining the Multilayer Perceptron'. Together they form a unique fingerprint.

Cite this