Brain-inspired chaotic spiking backpropagation

扫码查看

原文链接

NETL
NSTL
万方数据

外文摘要：Spiking neural networks(SNNs)have superior energy efficiency due to their spiking signal transmission,which mimics biological nervous systems,but they are difficult to train effectively.Although surrogate gradient-based methods offer a workable solution,trained SNNs frequently fall into local minima because they are still primarily based on gradient dynamics.Inspired by the chaotic dynamics in animal brain learning,we propose a chaotic spiking backpropagation(CSBP)method that introduces a loss function to generate brain-like chaotic dynamics and further takes advantage of the ergodic and pseudo-random nature to make SNN learning effective and robust.From a computational viewpoint,we found that CSBP significantly outperforms current state-of-the-art methods on both neuromorphic data sets(e.g.DVS-CIFAR10 and DVS-Gesture)and large-scale static data sets(e.g.CIFAR100 and ImageNet)in terms of accuracy and robustness.From a theoretical viewpoint,we show that the learning process of CSBP is initially chaotic,then subject to various bifurcations and eventually converges to gradient dynamics,consistently with the observation of animal brain activity.Our work provides a superior core tool for direct SNN training and offers new insights into understanding the learning process of a biological brain.

外文关键词：

spiking neural networkssurrogate gradientlocal minimabackpropagationbrain-inspired learningchaos

作者：

Zijian Wang、Peng Tao、Luonan Chen

展开 >

作者单位：

Key Laboratory of Systems Health Science of Zhejiang Province,School of Life Science,Hangzhou Institute for Advanced Study,University of Chinese Academy of Sciences,Hangzhou 310024,China

Key Laboratory of Systems Biology,Shanghai Institute of Biochemistry and Cell Biology,Center for Excellence in Molecular Cell Science,Chinese Academy of Sciences,Shanghai 200031,China

Guangdong Institute of Intelligence Science and Technology,Hengqin,Zhuhai 519031,China

Pazhou Laboratory(Huangpu),Guangzhou 510555,China

展开 >

基金：

National Natural Science Foundation of ChinaNational Natural Science Foundation of ChinaNational Natural Science Foundation of ChinaNational Natural Science Foundation of ChinaSpecial Fund for Science and Technology Innovation Strategy of Guangdong ProvinceSpecial Fund for Science and Technology Innovation Strategy of Guangdong ProvinceNational Key R&D Program of ChinaStrategic Priority Research Program of the Chinese Academy of SciencesJST Moonshot R&D

项目编号：

T2350003T234100712131020319300222021B09090500042021B09090600022022YFA1004800XDB38040400JPMJMS2021

出版年：

2024

DOI：

10.1093/nsr/nwae037

国家科学评论(英文版)

CSTPCD

ISSN：

年,卷(期)：2024.11(6)