Cargando…
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...
Autores principales: | Rueckert, Elmar, Kappel, David, Tanneberg, Daniel, Pecevski, Dejan, Peters, Jan |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group
2016
|
Materias: | |
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 |
Ejemplares similares
-
Probabilistic Inference in General Graphical Models through Sampling in Stochastic Networks of Spiking Neurons
por: Pecevski, Dejan, et al.
Publicado: (2011) -
NEVESIM: event-driven neural simulation framework with a Python interface
por: Pecevski, Dejan, et al.
Publicado: (2014) -
Learning Probabilistic Inference through Spike-Timing-Dependent Plasticity123
por: Pecevski, Dejan, et al.
Publicado: (2016) -
A Learning Theory for Reward-Modulated Spike-Timing-Dependent
Plasticity with Application to Biofeedback
por: Legenstein, Robert, et al.
Publicado: (2008) -
Solving Constraint Satisfaction Problems with Networks of Spiking Neurons
por: Jonke, Zeno, et al.
Publicado: (2016)