Share Email Print

Proceedings Paper

Decision boundary and generalization performance of feed-forward networks with Gaussian lateral connections
Author(s): Ravi Kothari; David Ensley
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

The hidden layer neurons in a multi-layered feed-forward neural network serve a critical role. From one perspective, the hidden layer neurons establish (linear) decision boundaries in the feature space. These linear decision boundaries are then combined by succeeding layers leading to convex-open and thereafter arbitrarily shaped decision boundaries. In this paper we show that the use of unidirectional Gaussian lateral connections from a hidden layer neuron to an adjacent hidden layer leads to a much richer class of decision boundaries. In particular the proposed class of networks has the advantage of sigmoidal feed-forward networks (global characteristics) but with the added flexibility of being able to represent local structure. An algorithm to train the proposed network is presented and its training and validation performance shown using a simple classification problem.

Paper Details

Date Published: 25 March 1998
PDF: 8 pages
Proc. SPIE 3390, Applications and Science of Computational Intelligence, (25 March 1998); doi: 10.1117/12.304820
Show Author Affiliations
Ravi Kothari, Univ. of Cincinnati (United States)
David Ensley, Air Force Research Lab. (United States)

Published in SPIE Proceedings Vol. 3390:
Applications and Science of Computational Intelligence
Steven K. Rogers; David B. Fogel; James C. Bezdek; Bruno Bosacchi, Editor(s)

© SPIE. Terms of Use
Back to Top