Oct 31, 2018

Local online learning in recurrent networks with random feedback

BioRxiv : the Preprint Server for Biology
James M Murray

Abstract

A longstanding challenge for computational neuroscience has been the development of biologically plausible learning rules for recurrent neural networks (RNNs) enabling the production and processing of time-dependent signals such as those that might drive movement or facilitate working memory. Classic gradient-based algorithms for training RNNs have been available for decades, but they are inconsistent with known biological features of the brain, such as causality and locality. In this work we derive an approximation to gradient-based learning that comports with these biologically motivated constraints. Specifically, the online learning rule for the synaptic weights involves only local information about the pre- and postsynaptic activities, in addition to a random feedback projection of the RNN output error. In addition to providing mathematical arguments for the effectiveness of the new learning rule, we show through simulations that it can be used to train an RNN to successfully perform a variety of tasks. Finally, to overcome the difficulty of training an RNN over a very large number of timesteps, we propose an augmented circuit architecture that allows the RNN to concatenate short-duration patterns into sequences of longer d...Continue Reading

  • References
  • Citations

References

  • We're still populating references for this paper, please check back later.
  • References
  • Citations

Citations

  • This paper may not have been cited yet.

Mentioned in this Paper

Memory, Short-Term
Patterns
Brain
TRN-GTT2-1
Etiology
Neural Network Simulation
Synapses
Simulation
Learning

About this Paper

Related Feeds

BioRxiv & MedRxiv Preprints

BioRxiv and MedRxiv are the preprint servers for biology and health sciences respectively, operated by Cold Spring Harbor Laboratory. Here are the latest preprint articles (which are not peer-reviewed) from BioRxiv and MedRxiv.

Related Papers

Neural Networks : the Official Journal of the International Neural Network Society
Ilya Sutskever, Geoffrey Hinton
IEEE Transactions on Systems, Man, and Cybernetics. Part B, Cybernetics : a Publication of the IEEE Systems, Man, and Cybernetics Society
Lianfang TianZongyuan Mao
BioRxiv : the Preprint Server for Biology
Nicolas Y MasseDavid J Freedman
© 2020 Meta ULC. All rights reserved