Recurrent Spiking Networks Solve Planning Tasks

A recurrent spiking neural network is proposed that implements planning as probabilistic inference for finite and infinite horizon tasks. The architecture splits this problem into two parts: The stochastic transient firing of the network embodies the dynamics of the planning task. With appropriate i...

Descripción completa

Detalles Bibliográficos
Autores principales: Rueckert, Elmar, Kappel, David, Tanneberg, Daniel, Pecevski, Dejan, Peters, Jan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group 2016
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4758071/
https://www.ncbi.nlm.nih.gov/pubmed/26888174
http://dx.doi.org/10.1038/srep21142

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4758071/
https://www.ncbi.nlm.nih.gov/pubmed/26888174
http://dx.doi.org/10.1038/srep21142

Ejemplares similares