UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

The Evolution of Training Parameters for Spiking Neural Networks with Hebbian Learning

Kozdon, KW; Bentley, P; (2018) The Evolution of Training Parameters for Spiking Neural Networks with Hebbian Learning. In: Ikegami, T and Virgo, N and Witkowski, O and Oka, M and Suzuki, R and Iizuka, H, (eds.) ALIFE 2018: The 2018 Conference on Artificial Life. (pp. pp. 276-283). MIT Press Green open access

[img]
Preview
Text
Kozdon, Bentley 2018 The Evolution of Training Parameters for Spiking Neural Networks with Hebbian Learning.pdf - ["content_typename_Accepted version" not defined]

Download (1MB) | Preview

Abstract

Spiking neural networks, thanks to their sensitivity to the timing of the inputs, are a promising tool for unsupervised processing of spatio-temporal data. However, they do not perform as well as the traditional machine learning approaches and their real-world applications are still limited. Various supervised and reinforcement learning methods for optimising spiking neural networks have been proposed, but more recently the evolutionary approach regained attention as a tool for training neural networks. Here, we describe a simple evolutionary approach for optimising spiking neural networks. This is the first published use of evolutionary algorithm to develop hyperparameters for fully unsupervised spike-timing- dependent learning for pattern clustering using spiking neural networks. Our results show that combining evolution and unsupervised learning leads to faster convergence on the optimal solutions, better stability of fit solutions and higher fitness of the whole population than using each approach separately.

Type: Proceedings paper
Title: The Evolution of Training Parameters for Spiking Neural Networks with Hebbian Learning
Event: ALIFE 2018: The 2018 Conference on Artificial Life, 23-27 July 2018, Tokyo, Japan
Location: Tokyo
Open access status: An open access version is available from UCL Discovery
DOI: 10.1162/isal_a_00055
Publisher version: https://doi.org/10.1162/isal_a_00055
Language: English
Additional information: © 2018 Massachusetts Institute of Technology. Published under a Creative Commons Attribution 4.0 International (CC BY 4.0) license (https://creativecommons.org/licenses/by/4.0/).
URI: http://discovery.ucl.ac.uk/id/eprint/10054192
Downloads since deposit
8Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item