A Radial Basis Function Spike Model for Indirect Learning via Integrate-and-Fire Sampling and Reconstruction Techniques.pdfVIP

Hindawi Publishing Corporation Advances in Artificial Neural Systems Volume 2012, Article ID 713581, 16 pages doi:10.1155/2012/713581 Research Article A Radial Basis Function Spike Model for Indirect Learning via Integrate-and-Fire Sampling and Reconstruction Techniques X. Zhang,1 G. Foderaro,1 C. Henriquez,2 A. M. J. VanDongen,3 and S. Ferrari1 1 Laboratory for Intelligent Systems and Control (LISC), Department of Mechanical Engineering and Materials Science, Duke University, Durham, NC 27708, USA 2 Department of Biomedical Engineering and Department of Computer Science, Duke University Durham, NC 27708, USA 3 Program in Neuroscience Behavioral Disorders, Duke-NUS Graduate Medical School, Singapore, Singapore Correspondence should be addressed to S. Ferrari, sferrari@ Received 17 February 2012; Accepted 21 May 2012 Academic Editor: Olivier Bastien Copyright © 2012 X. Zhang et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. This paper presents a deterministic and adaptive spike model derived from radial basis functions and a leaky integrate-and- fire sampler developed for training spiking neural networks without direct weight manipulation. Several algorithms have been proposed for training spiking neural networks through biologically-plausible learning mechanisms, such as spike-timing- dependent synaptic plasticity and Hebbian plasticity. These algorithms typically rely on the ability to update the synaptic strengths, or weights, directly, through a weight update rule in which the weight increment can be decided and implemented based on the training equations. However, in several potentia