An investigation of the effects of variable vigilance within the RePART neuro-fuzzy network

Canuto, Anne and Howells, Gareth and Fairhurst, Michael (2000) An investigation of the effects of variable vigilance within the RePART neuro-fuzzy network. Journal of Intelligent & Robotic Systems, 29 (4). pp. 317-334. ISSN 0921-0296. (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. (Contact us about this Publication)
Official URL
http:dx.doi.org/10.1023/A:1008159908688

Abstract

RePART is a variation of fuzzy ARTMAP to which a reward/punishment concept has been added. Previously, an improvement in performance of RePART had been noted compared with other ARTMAP-based models, such as fuzzy ARTMAP and ARTMAP-IC. In this paper, a wider investigation of RePART performance is described, in which RePART is analysed in relation to a multi-layer perceptron and a RAM-based network in a handwritten numeral recognition task. In the RePART network, a variable vigilance parameter is proposed in order to smooth the poor-generalisation problem of RePART. Firstly, the same vigilance is associated within every neuron general variable vigilance. Secondly, an individual variable vigilance for each neuron - which takes into account its average and Frequency of activation - is used. In a handwritten numeral recognition task using individual variable vigilance, RePART performance improved and demonstrated a performance comparable with alternative architectures such as fuzzy multi-layer perceptron and Radial RAM.

Item Type: Article
Uncontrolled keywords: fuzzy ARTMAP; reward/punishment parameter; RePART; fuzzy multi-layer perceptron; radial RAM; variable vigilance parameter; handwritten numeral recognition
Subjects: Q Science > QA Mathematics (inc Computing science) > QA 75 Electronic computers. Computer science
Divisions: Faculties > Science Technology and Medical Studies > School of Computing
Depositing User: P. Ogbuji
Date Deposited: 09 Apr 2009 11:57
Last Modified: 23 May 2014 09:24
Resource URI: https://kar.kent.ac.uk/id/eprint/16214 (The current URI for this page, for reference purposes)
  • Depositors only (login required):