Canuto, A. and Howells, G. and Fairhurst, M.C. (1999) RePART: A modified fuzzy ARTMAP for pattern recognition. LECTURE NOTES IN COMPUTER SCIENCE, 1625 . pp. 159-168. ISSN 0302-9743.
| The full text of this publication is not available from this repository. (Contact us about this Publication) | |
| Official URL http://dx.doi.org/10.1007/3-540-48774-3_19 |
Abstract
Fuzzy ARTMAP has been proposed as a neural network architecture for supervised learning of recognition categories and multidimensional maps in response to arbitrary sequences of analog or binary input vectors [12]. In this paper, RePART, a proposal for a variant of Fuzzy ARTMAP is analysed. As in ARTMAP-IC, this variant uses distributed code processing and instance counting in order to calculate the set of neurons used to predict untrained data. However, it additionally uses a reward/punishment process and takes into account every neuron in the calculation process..
| Item Type: | Article |
|---|---|
| Subjects: | Q Science > Q Science (General) T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisions: | Faculties > Science Technology and Medical Studies > School of Engineering and Digital Arts |
| Depositing User: | M. Nasiriavanaki |
| Date Deposited: | 30 Jun 2009 06:33 |
| Last Modified: | 30 Jun 2009 06:33 |
| Resource URI: | http://kar.kent.ac.uk/id/eprint/17181 (The current URI for this page, for reference purposes) |
- Depositors only (login required):
