STSF: Spiking Time Sparse Feedback Learning for Spiking Neural Networks

被引:0
作者
He, Ping [1 ,2 ]
Xiao, Rong [1 ,2 ]
Tang, Chenwei [1 ,2 ]
Huang, Shudong [1 ,2 ]
Lv, Jiancheng [1 ,2 ]
Tang, Huajin [3 ]
机构
[1] Sichuan Univ, Coll Comp Sci, Chengdu 610065, Peoples R China
[2] Minist Educ, Engn Res Ctr Machine Learning & Ind Intelligence, Chengdu 610065, Peoples R China
[3] Zhejiang Univ, Coll Comp Sci & Technol, Hangzhou 310027, Peoples R China
基金
中国国家自然科学基金;
关键词
Global-local spiking learning; sparse direct feedback alignment (DFA); spiking neural networks (SNNs); vanilla spike-timing-dependent plasticity (STDP); OPTIMIZATION; PLASTICITY; NEURONS;
D O I
10.1109/TNNLS.2025.3527700
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Spiking neural networks (SNNs) are biologically plausible models known for their computational efficiency. A significant advantage of SNNs lies in the binary information transmission through spike trains, eliminating the need for multiplication operations. However, due to the spatio-temporal nature of SNNs, direct application of traditional backpropagation (BP) training still results in significant computational costs. Meanwhile, learning methods based on unsupervised synaptic plasticity provide an alternative for training SNNs but often yield suboptimal results. Thus, efficiently training high-accuracy SNNs remains a challenge. In this article, we propose a highly efficient and biologically plausible spiking time sparse feedback (STSF) learning method. This algorithm modifies synaptic weights by incorporating a neuromodulator for global supervised learning using sparse direct feedback alignment (DFA) and local homeostasis learning with vanilla spike-timing-dependent plasticity (STDP). Such neuromorphic global-local learning focuses on instantaneous synaptic activity, enabling independent and simultaneous optimization of each network layer, thereby improving biological plausibility, enhancing parallelism, and reducing storage overhead. Incorporating sparse fixed random feedback connections for global error modulation, which uses selection operations instead of multiplication operations, further improves computational efficiency. Experimental results demonstrate that the proposed algorithm markedly reduces the computational cost with significantly higher accuracy comparable to current state-of-the-art algorithms across a wide range of classification tasks. Our implementation codes are available at https://github.com/hppeace/STSF.
引用
收藏
页码:11479 / 11492
页数:14
相关论文
共 50 条
[41]   Supervised learning in spiking neural networks: A review of algorithms and evaluations [J].
Wang, Xiangwen ;
Lin, Xianghong ;
Dang, Xiaochao .
NEURAL NETWORKS, 2020, 125 :258-280
[42]   Photonic Spiking Neural Networks and Graphene-on-Silicon Spiking Neurons [J].
Jha, Aashu ;
Huang, Chaoran ;
Peng, Hsuan-Tung ;
Shastri, Bhavin ;
Prucnal, Paul R. .
JOURNAL OF LIGHTWAVE TECHNOLOGY, 2022, 40 (09) :2901-2914
[43]   Supervised Learning With First-to-Spike Decoding in Multilayer Spiking Neural Networks [J].
Gardner, Brian ;
Gruening, Andre .
FRONTIERS IN COMPUTATIONAL NEUROSCIENCE, 2021, 15
[44]   Sparse and burst spiking in artificial neural networks inspired by synaptic retrograde signaling [J].
Faghihi, Faramarz ;
Moustafa, Ahmed A. .
INFORMATION SCIENCES, 2017, 421 :30-42
[45]   Biologically Plausible Models of Homeostasis and STDP: Stability and Learning in Spiking Neural Networks [J].
Carlson, Kristofor D. ;
Richert, Micah ;
Dutt, Nikil ;
Krichmar, Jeffrey L. .
2013 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2013,
[46]   Event and Time Driven Hybrid Simulation of Spiking Neural Networks [J].
Garrido, Jesus A. ;
Carrillo, Richard R. ;
Luque, Niceto R. ;
Ros, Eduardo .
Advances in Computational Intelligence, IWANN 2011, Pt I, 2011, 6691 :554-561
[47]   Multivariate Time Series Classification Using Spiking Neural Networks [J].
Fang, Haowen ;
Shrestha, Amar ;
Qiu, Qinru .
2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
[48]   Incremental Neural Synthesis for Spiking Neural Networks [J].
Huy Le Nguyen ;
Chu, Dominique .
2022 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI), 2022, :649-656
[49]   Topological Evolution of Spiking Neural Networks [J].
Slade, Sam ;
Zhang, Li .
2018 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2018,
[50]   Theoretically Provable Spiking Neural Networks [J].
Zhang, Shao-Qun ;
Zhou, Zhi-Hua .
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,