脉冲神经网络基准测试及类脑训练框架性能评估

doi:10.3969/j.issn.0255-8297.2025.01.012

应用科学学报 ›› 2025, Vol. 43 ›› Issue (1): 169-182.doi: 10.3969/j.issn.0255-8297.2025.01.012

脉冲神经网络基准测试及类脑训练框架性能评估

胡汪鑫^1,2, 成英超¹, 何玉林¹, 黄哲学^1,2, 蔡占川³

1. 人工智能与数字经济广东省实验室(深圳), 广东深圳 518107;
2. 深圳大学计算机与软件学院, 广东深圳 518060;
3. 澳门科技大学计算机科学与工程学院, 澳门 999078

收稿日期:2024-08-08 出版日期:2025-01-30 发布日期:2025-01-24
通信作者: 成英超，副研究员，研究方向为人工智能、机器学习与数据挖掘、新型算力网络智能计算。E-mail:chengyingchao@gml.ac.cn E-mail:chengyingchao@gml.ac.cn
基金资助:
广东省基础与应用基础研究基金重点项目（No.2023B1515120020）；广东省自然科学基金面上项目（No.2023A1515011667）；深圳市基础研究项目（No.JCYJ20220818100205012,No.JCYJ20210324093609026）资助

Benchmarking of Spiking Neural Networks and Performance Evaluation of Neuromorphic Training Frameworks

HU Wangxin^1,2, CHENG Yingchao¹, HE Yulin¹, HUANG Zhexue^1,2, CAI Zhanchuan³

1. Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen), Shenzhen 518107, Guangdong, China;
2. College of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, Guangdong, China;
3. School of Computer Science and Engineering, Macau University of Science and Technology, Macao 999078, China

Received:2024-08-08 Online:2025-01-30 Published:2025-01-24

摘要/Abstract

摘要： 随着脉冲神经网络（spiking neural network,SNN）研究需求的不断增长，开源类脑训练框架也迅速发展。然而，目前缺乏针对这些框架的系统性选择指南。为了解决该问题，提出了一种基于图像分类任务的SNN基准测试方法。本文为两种SNN训练方法，即直接替代梯度反向传播训练方法以及从人工神经网络（artificial neural network,ANN）到SNN的转换训练方法分别设计了卷积神经网络和全连接深度神经网络模型，并使用MNIST、Fashion-MNIST和CIFAR-10基准图像数据集，以训练时间和分类准确率为评估指标，比较了不同类脑训练框架的性能差异。研究结果表明，在SNN直接训练中，类脑训练框架SpikingJelly在训练时间和分类准确率方面均表现优异；而在ANN到SNN的转换训练中，Lava框架实现了最高的分类准确率。

关键词: 深度学习, 脉冲神经网络, 类脑训练框架, 基准测试, 图像分类

Abstract: With the growing interest in spiking neural networks (SNNs), the development of open-source neuromorphic training frameworks has also accelerated. However, there is currently a lack of systematic guidelines for selecting these frameworks. To address this issue, this paper proposes a benchmarking method for SNNs based on image classification tasks. This method designs a convolutional neural network and a fully connected deep neural networks to evaluate two SNN training approaches: direct training with surrogate gradient backpropagation and conversion from artificial neural networks (ANNs) to SNNs. Based on the MNIST, Fashion-MNIST, and CIFAR-10 benchmark image datasets, the performance comparisons of various neuromorphic training frameworks are conducted using evaluation metrics such as training time and classification accuracy. Experimental results indicate that the neuromorphic training framework SpikingJelly outperforms others in terms of both training time and classification accuracy in direct SNN training, while the Lava framework achieves the highest classification accuracy in ANN-to-SNN conversion training.

Key words: deep learning, spiking neural network, neuromorphic training framework, benchmarking, image classification

中图分类号:

TP183

胡汪鑫, 成英超, 何玉林, 黄哲学, 蔡占川. 脉冲神经网络基准测试及类脑训练框架性能评估[J]. 应用科学学报, 2025, 43(1): 169-182.

HU Wangxin, CHENG Yingchao, HE Yulin, HUANG Zhexue, CAI Zhanchuan. Benchmarking of Spiking Neural Networks and Performance Evaluation of Neuromorphic Training Frameworks[J]. Journal of Applied Sciences, 2025, 43(1): 169-182.

参考文献

[1] 郑南宁. 人工智能新时代[J]. 智能科学与技术学报, 2019, 1(1): 1-3. Zheng N N. The new era of artificial intelligence [J]. Chinese Journal of Intelligent Science and Technology, 2019, 1(1): 1-3. (in Chinese)
[2] 黄铁军, 余肇飞, 刘怡俊. 类脑机的思想与体系结构综述[J]. 计算机研究与发展, 2019, 56(6): 1135-1148. Huang T J, Yu Z F, Liu Y J. Brain-like machine: thought and architecture [J]. Journal of Computer Research and Development, 2019, 56(6): 1135-1148. (in Chinese)
[3] 张铁林, 徐波. 脉冲神经网络研究现状及展望[J]. 计算机学报, 2021, 44(9): 1767-1785. Zhang T L, Xu B. Research advances and perspectives on spiking neural networks [J]. Chinese Journal of Computers, 2021, 44(9): 1767-1785. (in Chinese)
[4] Roy K, Jaiswal A, Panda P. Towards spike-based machine intelligence with neuromorphic computing [J]. Nature, 2019, 575(7784): 607-617.
[5] Rathi N, Chakraborty I, Kosta A, et al. Exploring neuromorphic computing based on spiking neural networks: algorithms to hardware [J]. ACM Computing Surveys, 2023, 55(12): 1-49.
[6] Yang S M, Chen B D. Effective surrogate gradient learning with high-order information bottleneck for spike-based machine intelligence [J]. IEEE Transactions on Neural Networks and Learning Systems, 2023, 34(8): 1-15.
[7] Mostafa H. Supervised learning based on temporal coding in spiking neural networks [J]. IEEE Transactions on Neural Networks and Learning Systems, 2018, 29(7): 3227-3235.
[8] Bu T, Ding J, Yu Z, et al. Optimized potential initialization for low-latency spiking neural networks [C]//36th AAAI Conference on Artificial Intelligence, 2022: 11-20.
[9] Hao Z, Bu T, Ding J, et al. Reducing ANN-SNN conversion error through residual membrane potential [J]//37th AAAI Conference on Artificial Intelligence, 2023: 11-21.
[10] Baltes M, Abuhajar N, Yue Y, et al. Joint ANN-SNN co-training for object localization and image segmentation [C]//IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023: 1-5.
[11] Bu T, Fang W, Ding J, et al. Optimal ANN-SNN conversion for high-accuracy and ultra-lowlatency spiking neural networks [DB/OL]. 2023[2024-08-08]. https://arxiv.org/abs/2303.04347.
[12] Hu Y F, Tang H J, Pan G. Spiking deep residual networks [J]. IEEE Transactions on Neural Networks and Learning Systems, 2023, 34(8): 5200-5205.
[13] Zenke F, Ganguli S. SuperSpike: supervised learning in multilayer spiking neural networks [J]. Neural Computation, 2018, 30(6): 1514-1541.
[14] Javanshir A, Nguyen T, Mahmud M, et al. Advancements in algorithms and neuromorphic hardware for spiking neural networks [J]. Neural Computation, 2022, 34(6): 1289-1328.
[15] Wang Y, Shi K, Lu C, et al. Spatial-temporal self-attention for asynchronous spiking neural networks [C]//32nd International Joint Conference on Artificial Intelligence, 2023: 3085-3093.
[16] 张铁林, 李澄宇, 王刚, 等. 适合类脑脉冲神经网络的应用任务范式分析与展望[J]. 电子与信息学报, 2023, 45(8): 2675-2688. Zhang T L, Li C Y, Wang G, et al. Research advances and new paradigms for biologyinspired spiking neural networks [J]. Journal of Electronics & Information Technology, 2023, 45(8): 2675-2688. (in Chinese)
[17] Fang W, Chen Y, Ding J, et al. SpikingJelly: an open-source machine learning infrastructure platform for spike-based intelligence [J]. Science Advances, 2023, 9(40): eadi1480.
[18] Lecun Y, Bottou L, Bengio Y, et al. Gradient-based learning applied to document recognition [J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324.
[19] Xiao H, Rasul K, Vollgraf R. Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms [DB/OL]. 2017[2024-08-08]. https://arxiv.org/abs/1708.07747.
[20] Krizhevsky A. Learning multiple layers of features from tiny images [R]. Toronto: University of Toronto, 2009.
[21] 姜晓勇, 李忠义, 黄朗月, 等. 神经网络剪枝技术研究综述[J]. 应用科学学报, 2022, 40(5): 838-849. Jiang X Y, Li Z Y, Huang L Y, et al. Review of neural network pruning techniques [J]. Journal of Applied Sciences, 2022, 40(5): 838-849. (in Chinese)
[22] Lyu C Z, Xu J H, Zheng X Q. Spiking convolutional neural networks for text classification [C]//11th International Conference on Learning Representations, 2023: 1-17.
[23] Miikkulainen R, Liang J, Meyerson E, et al. Evolving deep neural networks [DB/OL]. 2017[2024-08-08]. https://arxiv.org/abs/1703.00548.
[24] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting [J]. Journal of Machine Learning Research, 2014, 15(1): 1929-1958.
[25] Kinouchi O, Pazzini R, Copelli M. Mechanisms of self-organized quasicriticality in neuronal network models [J]. Frontiers in Physics, 2020, 8: 583213.
[26] Szeliski R. Computer vision: algorithms and applications [M]. New York: Springer-Verlag, 2010: 1-28.
[27] Viet N H C. Spike-based hybrid learning method for image recognition task [C]//Proceedings of the 20249th International Conference on Intelligent Information Technology, 2024: 124-133.
[28] 岳斌. 基于脉冲神经网络的手写数字识别系统的设计与实现[D]. 北京: 中国科学院大学, 2022.

脉冲神经网络基准测试及类脑训练框架性能评估

Benchmarking of Spiking Neural Networks and Performance Evaluation of Neuromorphic Training Frameworks

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王莹笑, 杨彦红, 谭云峰. 面向视频的人脸特征计算方法[J]. 应用科学学报, 2025, 43(1): 137-153.
[2]	刘珈宁, 张思佳, 张正龙, 王祎涵, 安宗诗. 基于多跳机制的扩散图谱推荐模型[J]. 应用科学学报, 2025, 43(1): 123-136.
[3]	贾志洋, 许兆, 冷艳梅, 闻新, 龚浩宇. 基于并行优化CBAM的轻量级故障诊断模型[J]. 应用科学学报, 2025, 43(1): 94-109.
[4]	段新涛, 白鹿伟, 徐凯欧, 张萌, 保梦茹, 武银行, 秦川. 基于卷积神经网络的轻量高效图像隐写[J]. 应用科学学报, 2025, 43(1): 80-93.
[5]	王冰轮, 方巍. 基于U-Net改进的日平均2 m气温订正方法[J]. 应用科学学报, 2025, 43(1): 51-65.
[6]	唐意恒, 王永雄, 王哲, 张晓理. 基于子领域适应和时空学习的脑电情感识别[J]. 应用科学学报, 2024, 42(6): 1016-1026.
[7]	贺加贝, 周菊香, 甘健侯, 吴迪, 温晓宇. 基于多任务学习的课堂表情分类模型[J]. 应用科学学报, 2024, 42(6): 947-961.
[8]	栗莎, 王永雄, 王哲, 陈旭, 何嘉欣. 融合局部和全局特征的铸件缺陷检测[J]. 应用科学学报, 2024, 42(5): 757-768.
[9]	王子驰, 李斌, 冯国瑞, 张新鹏. 数字图像隐写分析综述[J]. 应用科学学报, 2024, 42(5): 723-732.
[10]	王娜, 朱会娟, 宋香梅, 冯霞. 一种基于领域自适应的智能合约安全分析框架[J]. 应用科学学报, 2024, 42(4): 585-597.
[11]	李子杰, 张姝, 欧阳昭相, 王俊, 吴迪. 基于场因子分解的xDeepFM推荐模型[J]. 应用科学学报, 2024, 42(3): 513-524.
[12]	严子杰, 王杨, 陈雁, 张翀. 基于层一致性平均教师模型的半监督岩石薄片图像分类[J]. 应用科学学报, 2024, 42(1): 27-38.
[13]	沈坤烨, 周晓飞, 费晓波, 陈雨中, 张继勇, 颜成钢. 基于边缘感知深度残差网络的带钢表面缺陷检测[J]. 应用科学学报, 2023, 41(6): 978-988.
[14]	张春森, 朱江乐, 张学芬, 刘旭东, 史书. 融合自注意力机制与生成对抗网络的DEM空洞填充[J]. 应用科学学报, 2023, 41(5): 789-800.
[15]	黄显培, 孟庆祥. 基于多特征卷积神经网络的哨兵二号影像地物分类[J]. 应用科学学报, 2023, 41(5): 766-776.