Allinson, Nigel and Johnson, Martin J. (1993) Self-organising N-tuple feature maps. Neural Network World, 5 . pp. 511-530. ISSN 1210-0552
| Documents |
| ||||
![[img]](http://eprints.lincoln.ac.uk/style/images/fileicons/application_pdf.png) |
PDF
[Untitled]-12.pdf - Whole Document Restricted to Repository staff only 5MB |
| Item Type: | Article |
|---|---|
| Item Status: | Live Archive |
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.
| 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 On: | 19 Apr 2012 15:53 |
Repository Staff Only: item control page