A spiking neural representation for XCSF

Howard, Gerard; Lanzi, Pier Luca; Howard, David; Bull, Larry

Abstract

This paper presents a Learning Classifier System (LCS) where each traditional rule is represented by a spiking neural network, a type of network with dynamic internal state. The evolutionary design process exploits parameter self-adaptation and a constructionist approach, providing the system with a flexible knowledge representation. It is shown how this approach allows for the evolution of networks of appropriate complexity to emerge whilst solving a continuous maze environment. Additionally, we extend the system to allow for temporal state decomposition. We evaluate our spiking neural LCS against one that uses Multi Layer Perceptron rules. © 2010 IEEE.

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 IEEE Congress on Evolutionary Computation, CEC 2010
• Start Date: Jul 18, 2010
• End Date: Jul 23, 2010
• Publication Date: Dec 1, 2010
• Peer Reviewed: Not Peer Reviewed
• DOI: https://doi.org/10.1109/CEC.2010.5586035
• Keywords: artificial neural networks, biological system modeling, brain models, neurons, robots, stability analysis
• Public URL: https://uwe-repository.worktribe.com/output/976887
• Publisher URL: http://dx.doi.org/10.1109/CEC.2010.5586035
• Additional Information: Title of Conference or Conference Proceedings : 2010 IEEE Congress on Evolutionary Computation (CEC)