RePART: A modified fuzzy ARTMAP for pattern recognition

Canuto, Anne and Howells, Gareth and Fairhurst, Michael (1999) RePART: A modified fuzzy ARTMAP for pattern recognition. Computational Intelligence, 1625 . pp. 159-168. ISSN 0824-7935. (The full text of this publication is not available from this repository)

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 Apr 2014 08:35
Resource URI: http://kar.kent.ac.uk/id/eprint/17181 (The current URI for this page, for reference purposes)
  • Depositors only (login required):