An accuracy-based neural classifier system

Bull, L. and O’Hara, T. (2001) An accuracy-based neural classifier system. Technical Report. Learning Classifier Systems Group, University of the West of England, Bristol, UK. Available from:

Full text not available from this repository

Publisher's URL:


Learning Classifier Systems have traditionally used a binary representation, with wildcards added to facilitate generalization. As they are applied to more complex domains the simple representation can become limiting. In this paper we present results from the use of a neural network-based representation scheme within the accuracy-based XCS. Here each rule's condition and action are represented by a small neural network, evolved through the actions of the genetic algorithm. After describing the changes required to the standard ...

Item Type:Report or Working Paper (Technical Report)
Uncontrolled Keywords:neural classifier system, computing
Faculty/Department:Faculty of Environment and Technology > Department of Computer Science and Creative Technologies
ID Code:20677
Deposited By: M. Clarke
Deposited On:24 Jul 2013 16:00
Last Modified:15 Nov 2016 22:21

Request a change to this item