Alladi Ramakrishnan Hall

A learning scheme for neural networks in the brain to predict and control body movement

Aditya Gilra

Laboratory of Computational Neuroscience, EPFL Lausanne, Switzerland

To plan and control movement, the brain must construct a model of the non-linear dynamics of the body in response to neuro-muscular commands. How a network of spiking neurons (in the brain) can learn such a model, by adjusting interconnection weights in a biologically plausible way, is still unresolved. As an advance in this direction, we propose a local and stable learning scheme, Feedback-based Online Local Learning Of Weights (FOLLOW) [Gilra and Gerstner, arXiv:1702.06463]. We show that the learning scheme is uniformly stable with the error going to zero asymptotically, under reasonable approximations. We apply the FOLLOW scheme to enable a network of interconnected spiking neurons to learn the dynamics of a linear, non-linear or chaotic example system. We also make the network learn the dynamics of a simplified two-link arm, then use the network to control the arm, to draw a desired shape on a wall. Ongoing extensions will also be discussed.