Gradient Learning in Networks of Smoothly Spiking Neurons

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F09%3A00318366" target="_blank" >RIV/67985807:_____/09:00318366 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Gradient Learning in Networks of Smoothly Spiking Neurons
Original language description
A slightly simplified version of the Spike Response Model SRM0 of a spiking neuron is tailored to gradient learning. In particular, the evolution of spike trains along the weight and delay parameter trajectories is made perfectly smooth. For this model aback-propagation-like learning rule is derived which propagates the error also along the time axis. This approach overcomes the difficulties with the discontinuous-in-time nature of spiking neurons, which encounter previous gradient learning algorithms(e.g. SpikeProp). The new algorithm can naturally cope with multiple spikes and preliminary experiments confirm the smoothness of spike creation/deletion process.
Czech name
—
Czech description
—

Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year
2009
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Advances in Neuro-Information Processing. Revised Selected Papers Part II
ISBN
978-3-642-03039-0
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
—
Publisher name
Springer
Place of publication
Berlin
Event location
Auckland
Event date
Nov 25, 2008
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000270578200022

Similar results(10)