A solution to the learning dilemma for recurrent networks of spiking neurons

Author:

Bellec Guillaume,Scherr Franz,Subramoney Anand,Hajek Elias,Salaj Darjan,Legenstein Robert,Maass Wolfgang

Abstract

AbstractRecurrently connected networks of spiking neurons underlie the astounding information processing capabilities of the brain. But in spite of extensive research, it has remained open how they can learn through synaptic plasticity to carry out complex network computations. We argue that two pieces of this puzzle were provided by experimental data from neuroscience. A new mathematical insight tells us how these pieces need to be combined to enable biologically plausible online network learning through gradient descent, in particular deep reinforcement learning. This new learning method – called e-prop – approaches the performance of BPTT (backpropagation through time), the best known method for training recurrent neural networks in machine learning. In addition, it suggests a method for powerful on-chip learning in novel energy-efficient spike-based hardware for AI.

Publisher

Cold Spring Harbor Laboratory

Reference59 articles.

1. LeCun, Y. , Bengio, Y. & Hinton, G. Deep learning. Nature (2015).

2. Allen Institute: Cell Types Database. ® 2018 Allen Institute for Brain Science. Allen Cell Types Database, cell feature search. Available from: celltypes.brain-map.org/data (2018).

3. Bellec, G. , Salaj, D. , Subramoney, A. , Legenstein, R. & Maass, W. Long short-term memory and learning-to-learn in networks of spiking neurons. NeurIPS (2018).

4. Huh, D. & Sejnowski, T. J. Gradient descent for spiking neural networks. NeurIPS (2018).

5. Lillicrap, T. P. & Santoro, A. Backpropagation through time and the brain. Current Opinion in Neurobiology (2019).

Cited by 18 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3