A cognitive architecture based on a learning classifier system with spiking classifiers

Howard, G. D., Bull, L. and Lanzi, P. L. (2016) A cognitive architecture based on a learning classifier system with spiking classifiers. Neural Processing Letters, 44 (1). pp. 125-147. ISSN 1370-4621 Available from: http://eprints.uwe.ac.uk/26410

PDF - Accepted Version
Available under License All Rights Reserved.


Publisher's URL: http://dx.doi.org/10.1007/s11063-015-9451-4


Learning classifier systems (LCS) are population-based reinforcement learners that were originally designed to model various cognitive phenomena. This paper presents an explicitly cognitive LCS by using spiking neural networks as classifiers, providing each classifier with a measure of temporal dynamism. We employ a constructivist model of growth of both neurons and synaptic connections, which permits a genetic algorithm to automatically evolve sufficiently-complex neural structures. The spiking classifiers are coupled with a temporally-sensitive reinforcement learning algorithm, which allows the system to perform temporal state decomposition by appropriately rewarding “macro-actions”, created by chaining together multiple atomic actions. The combination of temporal reinforcement learning and neural information processing is shown to outperform benchmark neural classifier systems, and successfully solve a robotic navigation task.

Item Type:Article
Additional Information:The final publication is available at Springer via http://dx.doi.org/10.1007/s11063-015-9451-4
Uncontrolled Keywords:evolution, neural network
Faculty/Department:Faculty of Environment and Technology > Department of Computer Science and Creative Technologies
ID Code:26410
Deposited By: Professor L. Bull
Deposited On:24 Aug 2015 14:13
Last Modified:24 Jan 2017 17:17

Request a change to this item

Total Document Downloads in Past 12 Months

Document Downloads

Total Document Downloads

More statistics for this item...