Connectionists: New Paper: Does high firing irregularity enhance learning?

[Chris Christodoulou]

Dear Colleagues,

I would like to announce the availability of the following paper that has been 
accepted and will appear in Neural Computation:

Christodoulou, C. and Cleanthous, A. 'Does high firing irregularity enhance 
learning?', Neural Computation (in press).

A preprint of the paper can be downloaded from:
http://www.cs.ucy.ac.cy/~cchrist/cc_ac_nc10_pprnt.pdf


Abstract
--------
In this paper, we demonstrate that the high firing irregularity produced 
by the leaky integrate-and-fire neuron with the partial somatic reset 
mechanism, which has been shown to be the most likely candidate to reflect 
the mechanism used in the brain for reproducing the highly irregular 
cortical neuron firing at high rates (Bugmann, Christodoulou & Taylor, 
Neural Comput. 9 (1997) 985; Christodoulou & Bugmann, Neurocomput. 38-40 
(2001) 1141), enhances learning. More specifically, it enhances 
reward-modulated Spike Timing-Dependent Plasticity with eligibility trace 
when used in spiking neural networks, as shown by the results when tested 
in the simple benchmark problem of XOR as well as in a complex multiagent 
setting task.

--------

Kind regards,

Chris Christodoulou

* * *
Dr Chris Christodoulou          cchrist at cs.ucy.ac.cy
Department of Computer Science, University of Cyprus
75 Kallipoleos Ave, P.O. Box 20537, 1678 Nicosia, Cyprus
Tel. (+357) 22 892752, Fax (+357) 22 892701