Self-organising N-tuple feature maps

Allinson, Nigel and Johnson, Martin J. (1993) Self-organising N-tuple feature maps. Neural Network World, 5 . pp. 511-530. ISSN 1210-0552

Documents
Self-organising N-tuple feature maps
[img]
[Download]
Request a copy
[img] PDF
[Untitled]-12.pdf - Whole Document
Restricted to Repository staff only

5MB

Abstract

A novel form of self-organising neural network, based on the N-tuple sampling of binary patterns, is presented. our approach is suited to the high-speed unsupervised topological learning of very high dimensional patterns using conventional digital components. The network is compared with the conventional Kohonen self-organising map. Applications outlined are the classification of characters, and weight vector and ideal pattern reconstruction.

Item Type:Article
Additional Information:A novel form of self-organising neural network, based on the N-tuple sampling of binary patterns, is presented. our approach is suited to the high-speed unsupervised topological learning of very high dimensional patterns using conventional digital components. The network is compared with the conventional Kohonen self-organising map. Applications outlined are the classification of characters, and weight vector and ideal pattern reconstruction.
Keywords:Pattern recognition, Neural networks, Unsupervised learning
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
Divisions:College of Science > School of Computer Science
ID Code:5019
Deposited By: Tammie Farley
Deposited On:19 Apr 2012 15:53
Last Modified:13 Mar 2013 09:05

Repository Staff Only: item control page