Paper Info
Title
Predicting non-linear dynamics: a stable local learning scheme for recurrent spiking neural networks.
Abstract
Brains need to predict how our muscles and body react to motor commands. How networks of spiking neurons can learn to reproduce these non-linear dynamics, using local, online and stable learning rules, is an important, open question. 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, while an online and local rule changes the weights; hence we call the scheme FOLLOW (Feedback-based Online Local Learning Of Weights) The rule is local in the sense that weight changes depend on the presynaptic activity and the error signal projected onto the post-synaptic neuron. We provide examples of learning linear, non-linear and chaotic dynamics, as well as the dynamics of a two-link arm. Using the Lyapunov method, and under reasonable assumptions and approximations, we show that FOLLOW learning is uniformly stable, with the error going to zero asymptotically.
Year
Venue
Field
2017
arXiv: Neurons and Cognition
Lyapunov function,Nonlinear system,Local learning,Control theory,Supervised learning,Error signal,Artificial intelligence,Chaotic,Spiking neural network,Machine learning,Mathematics,Feed forward
DocType
Volume
Citations 
Journal
abs/1702.06463
0
PageRank 
References 
Authors
0.34
15
2
Name
Order
Citations
PageRank
Aditya Gilra101.35
Wulfram Gerstner22437410.08