Share Email Print

Proceedings Paper

Incremental supervised learning: localized updates in nonlocalized networks
Author(s): Wendy Foslien; Tariq Samad
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We present a novel yet simple approach to incremental learning in neural networks: the problem of updating a mapping based on limited new data. The approach consists of forming a training set by appending to the new data additional training examples generated by exercising the network. This strategy enables the mapping to be updated in the neighborhood of the new data without causing distortions elsewhere in the input space. The approach can be used with any neural network model; it is particularly useful for the popular multilayer sigmoidal networks in which small parameter changes can have nonlocal consequences. Demonstrations and parametric explorations on a toy problem are described.

Paper Details

Date Published: 1 July 1992
PDF: 8 pages
Proc. SPIE 1710, Science of Artificial Neural Networks, (1 July 1992); doi: 10.1117/12.140156
Show Author Affiliations
Wendy Foslien, Honeywell Sensors & Systems Development Ctr. (United States)
Tariq Samad, Honeywell Sensors & Systems Development Ctr. (United States)

Published in SPIE Proceedings Vol. 1710:
Science of Artificial Neural Networks
Dennis W. Ruck, Editor(s)

© SPIE. Terms of Use
Back to Top