Rapidly reconfigurable dynamic computing in neural networks with fixed synaptic connectivity

Learning and memory in the brain’s neocortex have long been hypothesised to be primarily mediated by synaptic plasticity. Extensive research in artificial neural networks has shown that training networks by adjusting connection weights faces computational challenges, including large parameter spaces and the tendency of new learning to interfere with previous learning (catastrophic forgetting). We propose that the brain, which is resistant to these challenges, can also learn by modulating the excitability of each neuron in a network rather than changing synaptic strengths.

We show here that learning a task-specific set of bias currents enables a feedforward or recurrent network with fixed and randomly assigned connections to perform well on and switch between dozens of tasks, including regression, classification, autonomous time series generation, a game and motor control. Bias-only learning also provides a mechanistic account of how representational drift and structured neuron-level variability can coexist with stable population-level computation. W.N. is funded by an NSERC Discovery Grant (RGPIN/04568-2020), a Canada Research Chair (CRC-2019-00416), a Hotchkiss Brain Institute start-up grant and the Cumming Medical Research Fund.

A.G. is supported by NSERC (RGPIN/05347-202), Digital Research Alliance of Canada, Hotchkiss Brain Institute, Alberta Children’s Hospital Research Institute, and the Azrieli Accelerator. This research was partially funded by Synaptrain Technologies Inc. Department of Cell Biology and Anatomy, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada Creative Destruction Lab, Toronto, ON, Canada Department of Bioengineering, Faculty of Engineering, Imperial College London, London, UK W.N., A.G., and S.S. are the CSO, CPO, and CEO of Synaptrain Technologies Inc., respectively.

A provisional patent has been filed based on the research presented in this manuscript. All other authors declare no competing interest. A provisional patent has been filed in the US under serial number 63/867,999, reference number 339638.00005.

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it.

The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.