Library Header Image
LSE Research Online LSE Library Services

On constructing threshold networks for pattern classification

Anthony, Martin (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

Full text not available from this repository.


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:
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: 16 May 2024 05:18

Actions (login required)

View Item View Item