hebbRNN: A Reward-Modulated Hebbian Learning Rule for Recurrent Neural Networks
Jonathan A. Michaels, Hansjörg Scherberger · The Journal of Open Source Software · 2016
How does our brain learn to produce the large, impressive, and flexible array of motor behaviors we possess?In recent years, there has been renewed interest in modeling complex human behaviors such as memory and motor skills using neural networks (Sussillo et al. 2015;Rajan, Harvey, and Tank 2016;Hennequin, Vogels, and Gerstner 2014;Carnevale et al. 2015;Laje, Buonomano, and Buonomano 2013).However, training these networks to produce meaningful behavior has proven difficult.Furthermore, the most common methods are generally not biologically-plausible and rely on information not local to the synapses of individual neurons as well as instantaneous reward signals (Martens and Sutskever 2011;Sussillo and Abbott 2009;Song, Yang, and Wang 2016).