Anthony, Martin 
ORCID: 0000-0002-7796-6044
(2009)
On constructing threshold networks for pattern classification.
In: Franco, Leonardo, Elizondo, David A. and Jerez, José M., (eds.)
Constructive Neural Networks.
Studies in computational intelligence (258).
Springer Berlin / Heidelberg, Berlin, Germany, pp. 71-82.
ISBN 9783642045110
Abstract
This paper describes a method of constructing one-hidden layer feedforward linear threshold networks to represent Boolean functions (or partially-defined Boolean functions). The first step in the construction is sequential linear separation, a technique that has been used by a number of researchers [7, 11, 2]. Next, from a suitable sequence of linear separations, a threshold network is formed. The method described here results in a threshold network with one hidden layer. We compare this approach to the standard approach based on a Boolean function’s disjunctive normal form and to other approaches based on sequential linear separation [7, 11]
| Item Type: | Book Section |
|---|---|
| Official URL: | http://www.springer.com/ |
| Additional Information: | © 2009 Springer-Verlag Berlin Heidelberg |
| Divisions: | Mathematics |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics |
| Date Deposited: | 13 Aug 2010 11:19 |
| Last Modified: | 01 Nov 2024 04:37 |
| URI: | http://eprints.lse.ac.uk/id/eprint/28994 |
Actions (login required)
 |
View Item |
