Stochastic resonance and finite resolution in a network of leaky integrate-and-fire neurons

Mtetwa, N.; Smith, L.S.; Hussain, A.

Abstract

This paper discusses the effect of stochastic resonance in a network of leaky integrate-and-fire (LIF) neurons and investigates its realisation on a Field Programmable Gate Array (FPGA). We report in this study that stochastic resonance which is mainly associated with floating point implementations is possible in both a single LIF neuron and a network of LIF neurons implemented on lower resolution integer based digital hardware. We also report that such a network can improve the signal-to-noise ratio (SNR) of the output over a single LIF neuron.

Citation

Mtetwa, N., Smith, L., & Hussain, A. (2002, August). Stochastic resonance and finite resolution in a network of leaky integrate-and-fire neurons. Presented at ICANN: International Conference on Artificial Neural Networks, Madrid, Spain

• Presentation Conference Type: Conference Paper (published)
• Conference Name: ICANN: International Conference on Artificial Neural Networks
• Start Date: Aug 28, 2002
• End Date: Aug 30, 2002
• Online Publication Date: Aug 21, 2002
• Publication Date: 2002
• Deposit Date: Oct 16, 2019
• Publisher: Springer
• Pages: 117-122
• Series Title: Lecture Notes in Computer Science
• Series Number: 2415
• Series ISSN: 0302-9743
• Book Title: Artificial Neural Networks — ICANN 2002
• ISBN: 978-3-540-44074-1
• DOI: https://doi.org/10.1007/3-540-46084-5_20
• Public URL: http://researchrepository.napier.ac.uk/Output/1793763