Cargando…
Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network
The brain needs to predict how the body reacts to motor commands, but how a network of spiking neurons can learn non-linear body dynamics using local, online and stable learning rules is unclear. Here, we present a supervised learning scheme for the feedforward and recurrent connections in a network...
Autores principales: | Gilra, Aditya, Gerstner, Wulfram |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
eLife Sciences Publications, Ltd
2017
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5730383/ https://www.ncbi.nlm.nih.gov/pubmed/29173280 http://dx.doi.org/10.7554/eLife.28295 |
Ejemplares similares
-
Multi-Timescale Memory Dynamics Extend Task Repertoire in a Reinforcement Learning Network With Attention-Gated Memory
por: Martinolli, Marco, et al.
Publicado: (2018) -
Stochastic variational learning in recurrent spiking networks
por: Jimenez Rezende, Danilo, et al.
Publicado: (2014) -
Limits to high-speed simulations of spiking neural networks using general-purpose computers
por: Zenke, Friedemann, et al.
Publicado: (2014) -
Neuromodulated Spike-Timing-Dependent Plasticity, and Theory of Three-Factor Learning Rules
por: Frémaux, Nicolas, et al.
Publicado: (2016) -
Inference of neuronal network spike dynamics and topology from calcium imaging data
por: Lütcke, Henry, et al.
Publicado: (2013)