Predicting non-linear dynamics by stable local learning in a recurrent spiking neural network.

Content Provider	Europe PMC
Author	Gilra, Aditya Gerstner, Wulfram
Editor	Latham, Peter
Copyright Year	2017
Abstract	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 of heterogeneous spiking neurons. The error in the output is fed back through fixed random connections with a negative gain, causing the network to follow the desired dynamics. The rule for Feedback-based Online Local Learning Of Weights (FOLLOW) is local in the sense that weight changes depend on the presynaptic activity and the error signal projected onto the postsynaptic neuron. We provide examples of learning linear, non-linear and chaotic dynamics, as well as the dynamics of a two-link arm. Under reasonable approximations, we show, using the Lyapunov method, that FOLLOW learning is uniformly stable, with the error going to zero asymptotically.
Journal	eLife
Volume Number	6
PubMed Central reference number	PMC5730383
PubMed reference number	29173280
e-ISSN	2050084X
DOI	10.7554/elife.28295
Language	English
Publisher	eLife Sciences Publications, Ltd
Publisher Date	2017-11-27
Access Restriction	Open
Rights License	This article is distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use and redistribution provided that the original author and source are credited. © 2017, Gilra et al
Subject Keyword	learning motor control recurrent neural networks plasticity feedback stability
Content Type	Text
Resource Type	Article
Subject	Immunology and Microbiology Neuroscience Medicine Biochemistry, Genetics and Molecular Biology