Hebbian spike-timing dependent self-organization in pulsed neural networks

Christo Panchev, Stefan Wermter

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

Abstract

We present a mechanism of unsupervised competitive learning and development of topology preserving self-organizing maps of spiking neurons. The information encoding is based on the precise timing of single spike events. The work provides a competitive learning algorithm that is based on the relative timing of the pre- and post-synaptic spikes, local synapse competitions within a single neuron and global competition via lateral connections. Furthermore, we present part of the experimental work on the capability of the suggested mechanism to perform topology preserving mapping and competitive learning. The results show that our model covers the main characteristic behaviour of the standard SOM but uses a computationally more powerful timing-dependent spike encoding.
Original languageEnglish
Title of host publicationWorld Congress on Neuroinformatics
Subtitle of host publication[Vienna, Austria, Sept. 24-29, 2001]. Pt. 1 Proceedings
Place of PublicationVienna
PublisherARGESIM/ASIM 2001
Number of pages8
Publication statusPublished - 2001
Externally publishedYes
EventWorld Congress on Neuroinformatics - Vienna, Austria
Duration: 24 Sept 200129 Sept 2001

Conference

ConferenceWorld Congress on Neuroinformatics
Country/TerritoryAustria
CityVienna
Period24/09/0129/09/01

Fingerprint

Dive into the research topics of 'Hebbian spike-timing dependent self-organization in pulsed neural networks'. Together they form a unique fingerprint.

Cite this