Training Spiking Neural Networks Using Lessons From Deep Learning

Proceedings of the IEEE, vol. 111, pp. 1016–1054

Abstract

The brain is the perfect place to look for inspiration to develop more efficient neural networks. The inner workings of our synapses and neurons provide a glimpse at what the future of deep learning might look like. This article serves as a tutorial and perspective showing how to apply the lessons learned from several decades of research in deep learning, gradient descent, backpropagation, and neuroscience to biologically plausible spiking neural networks (SNNs). We also explore the delicate interplay between encoding data as spikes and the learning process; the challenges and solutions of applying gradient-based learning to SNNs; the subtle link between temporal backpropagation and spike timing-dependent plasticity; and how deep learning might move toward biologically plausible online learning. Some ideas are well accepted and commonly used among the neuromorphic engineering community, while others are presented or justified for the first time here. A series of companion interactive tutorials complementary to this article using our Python package,snnTorch, are also made available: https://snntorch.readthedocs.io/en/latest/tutorials/index.html.

Authors 9

1. Jason K. Eshraghian

   University of California, Santa Cruz · University of Michigan

   Affiliation as printed

   Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA

   Department of Electrical and Computer Engineering, University of California at Santa Cruz, Santa Cruz, CA, USA

2. Max Ward

   Harvard University · The University of Western Australia

   Affiliation as printed

   Department of Molecular and Cellular Biology, Harvard University, Cambridge, MA, USA

   Department of Computer Science and Software Engineering, The University of Western Australia, Crawley, WA, Australia

3. Emre Neftci Aachen Faculty of Electrical Engineering and Information Technology

   University of California, Irvine · RWTH Aachen University

   Affiliation as printed

   Department of Computer Science and the Department of Cognitive Sciences, University of California at Irvine (UC Irvine), Irvine, CA, USA

   Faculty of Electrical Engineering and Information Technology, RWTH Aachen University, Aachen, Germany

4. Xinxin Wang

   University of Michigan

   Affiliation as printed

   Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA

5. Gregor Lenz
   Affiliation as printed

   SynSense AG, Zürich, Switzerland

6. Girish Dwivedi

   The University of Western Australia

   Affiliation as printed

   School of Medicine, The University of Western Australia, Crawley, WA, Australia

7. Mohammed Bennamoun

   The University of Western Australia

   Affiliation as printed

   Department of Computer Science and Software Engineering, The University of Western Australia, Crawley, WA, Australia

8. Doo Seok Jeong

   Hanyang University

   Affiliation as printed

   Division of Materials Science and Engineering, Hanyang University, Seoul, South Korea

9. Wei Dong Lu

   University of Michigan

   Affiliation as printed

   Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, USA