Topological features of spike trains in recurrent spiking neural networks that are trained to generate spatiotemporal patterns

In this study, we focus on training recurrent spiking neural networks to generate spatiotemporal patterns in the form of closed two-dimensional trajectories. Spike trains in the trained networks are examined in terms of their dissimilarity using the Victor–Purpura distance. We apply algebraic topolo...

Volledige beschrijving

Bibliografische gegevens

Hoofdauteurs:	Oleg Maslennikov, Matjaž Perc, Vladimir Nekorkin
Formaat:	Artigo
Taal:	Inglês
Gepubliceerd in:	Frontiers Media S.A. 2024-02-01
Reeks:	Frontiers in Computational Neuroscience
Onderwerpen:	spiking neural network target spatiotemporal pattern supervised learning reservoir computing spike metrics persistent homology
Online toegang:	https://www.frontiersin.org/articles/10.3389/fncom.2024.1363514/full
Tags:	Voeg label toe Geen labels, Wees de eerste die dit record labelt!