Tampere University of Technology

TUTCRIS Research Portal

Pattern recognition with Spiking Neural Networks: a simple training method

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publicationProceedings pf the 14th Symposium on Programming Languages and Software Tools
EditorsJyrki Nummenmaa, Outi Sievi-Korte, Erkki Mäkinen
PublisherCEUR-WS.org
Pages296-308
Number of pages13
Publication statusPublished - 2015
Publication typeA4 Article in a conference publication
EventSymposium on Programming Languages and Software Tools -
Duration: 1 Jan 1900 → …

Publication series

NameCEUR Workshop Proceedings
Volume1525
ISSN (Electronic)1613-0073

Conference

ConferenceSymposium on Programming Languages and Software Tools
Period1/01/00 → …

Abstract

As computers are getting more pervasive, software becomes transferable to different types of hardware and, at the extreme, being bio-compatible. Recent efforts in Artificial Intelligence propose that software can be trained and taught instead of “hard-coded” sequences. This paper addresses the learnability of software in the context of platforms integrating biological components. A method for training Spiking Neural Networks (SNNs) for pattern recognition is proposed, based on spike timing dependent plasticity (STDP) of connections. STDP corresponds to the way connections between neurons change according to the spiking activity in the network, and we use STDP to stimulate outputs of the network shortly after feeding it with a pattern as input, thus creating specific pathways in the network. The computational model used to test this method through simulations is developed to fit the behaviour of biological neural networks, showing the potential for training neural cells into biological processors.

Publication forum classification

Field of science, Statistics Finland