Skip to main content

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

Publication ,  Journal Article
Zhang, X; Foderaro, G; Henriquez, C; VanDongen, AMJ; Ferrari, S
Published in: Advances in Artificial Neural Systems
October 10, 2012

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 potential applications of adaptive spiking neural networks, including neuroprosthetic devices and CMOS/memristor nanoscale neuromorphic chips, the weights cannot be manipulated directly and, instead, tend to change over time by virtue of the pre- and postsynaptic neural activity. This paper presents an indirect learning method that induces changes in the synaptic weights by modulating spike-timing-dependent plasticity by means of controlled input spike trains. In place of the weights, the algorithm manipulates the input spike trains used to stimulate the input neurons by determining a sequence of spike timings that minimize a desired objective function and, indirectly, induce the desired synaptic plasticity in the network.

Duke Scholars

Published In

Advances in Artificial Neural Systems

DOI

EISSN

1687-7608

ISSN

1687-7594

Publication Date

October 10, 2012

Volume

2012

Start / End Page

1 / 16

Publisher

Hindawi Limited

Related Subject Headings

  • 4611 Machine learning
  • 0801 Artificial Intelligence and Image Processing
  • 0102 Applied Mathematics
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Zhang, X., Foderaro, G., Henriquez, C., VanDongen, A. M. J., & Ferrari, S. (2012). A Radial Basis Function Spike Model for Indirect Learning via Integrate-and-Fire Sampling and Reconstruction Techniques. Advances in Artificial Neural Systems, 2012, 1–16. https://doi.org/10.1155/2012/713581
Zhang, X., G. Foderaro, C. Henriquez, A. M. J. VanDongen, and S. Ferrari. “A Radial Basis Function Spike Model for Indirect Learning via Integrate-and-Fire Sampling and Reconstruction Techniques.” Advances in Artificial Neural Systems 2012 (October 10, 2012): 1–16. https://doi.org/10.1155/2012/713581.
Zhang X, Foderaro G, Henriquez C, VanDongen AMJ, Ferrari S. A Radial Basis Function Spike Model for Indirect Learning via Integrate-and-Fire Sampling and Reconstruction Techniques. Advances in Artificial Neural Systems. 2012 Oct 10;2012:1–16.
Zhang, X., et al. “A Radial Basis Function Spike Model for Indirect Learning via Integrate-and-Fire Sampling and Reconstruction Techniques.” Advances in Artificial Neural Systems, vol. 2012, Hindawi Limited, Oct. 2012, pp. 1–16. Crossref, doi:10.1155/2012/713581.
Zhang X, Foderaro G, Henriquez C, VanDongen AMJ, Ferrari S. A Radial Basis Function Spike Model for Indirect Learning via Integrate-and-Fire Sampling and Reconstruction Techniques. Advances in Artificial Neural Systems. Hindawi Limited; 2012 Oct 10;2012:1–16.

Published In

Advances in Artificial Neural Systems

DOI

EISSN

1687-7608

ISSN

1687-7594

Publication Date

October 10, 2012

Volume

2012

Start / End Page

1 / 16

Publisher

Hindawi Limited

Related Subject Headings

  • 4611 Machine learning
  • 0801 Artificial Intelligence and Image Processing
  • 0102 Applied Mathematics