Affordable Access

On-line learning with minimal degradation in feedforward networks.

Authors
  • de Angulo, V R
  • Torras, C
Type
Published Article
Journal
IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council
Publication Date
Jan 01, 1995
Volume
6
Issue
3
Pages
657–668
Identifiers
PMID: 18263351
Source
Medline
License
Unknown

Abstract

Dealing with nonstationary processes requires quick adaptation while at the same time avoiding catastrophic forgetting. A neural learning technique that satisfies these requirements, without sacrificing the benefits of distributed representations, is presented. It relies on a formalization of the problem as the minimization of the error over the previously learned input-output patterns, subject to the constraint of perfect encoding of the new pattern. Then this constrained optimization problem is transformed into an unconstrained one with hidden-unit activations as variables. This new formulation leads to an algorithm for solving the problem, which we call learning with minimal degradation (LMD). Some experimental comparisons of the performance of LMD with backpropagation are provided which, besides showing the advantages of using LMD, reveal the dependence of forgetting on the learning rate in backpropagation. We also explain why overtraining affects forgetting and fault tolerance, which are seen as related problems.

Report this publication

Statistics

Seen <100 times