University of Hertfordshire

By the same authors

Evolving spiking neural networks for temporal pattern recognition in the presence of noise

Research output: Chapter in Book/Report/Conference proceedingConference contribution

View graph of relations
Original languageEnglish
Title of host publicationArtificial Life 2014
Subtitle of host publicationProcs of the Fourteenth International Conference on the Synthesis and Simulation of Living Systems
EditorsHiroki Sayama
PublisherMIT Press
Pages965-972
DOIs
StatePublished - 2014
EventArtificial Life 2014 - New York, United States

Conference

ConferenceArtificial Life 2014
CountryUnited States
CityNew York
Period30/07/14 → …

Abstract

Nervous systems of biological organisms use temporal patterns of spikes to encode sensory input, but the mechanisms that underlie the recognition of such patterns are unclear.
In the present work, we explore how networks of spiking neurons can be evolved to recognize temporal input patterns without being able to adjust signal conduction delays. We evolve the networks with GReaNs, an artificial life platform
that encodes the topology of the network (and the weights of connections) in a fashion inspired by the encoding of gene regulatory networks in biological genomes. The number of computational nodes or connections is not limited in GReaNs, but here we limit the size of the networks to analyze the functioning of the networks and the effect of network size on the evolvability of robustness to noise. Our results show that even very small networks of spiking neurons can perform temporal pattern recognition in the presence of input noise

Notes

Creative Commons - Attribution-NonCommercial-NoDerivs 3.0 United States

Projects

ID: 7520278