深度尖峰神经网络的逐步加权尖峰编码

Yiwen Gu, Junchuan Gu, Haibin Shen, Kejie Huang
{"title":"深度尖峰神经网络的逐步加权尖峰编码","authors":"Yiwen Gu, Junchuan Gu, Haibin Shen, Kejie Huang","doi":"arxiv-2408.17245","DOIUrl":null,"url":null,"abstract":"Spiking Neural Networks (SNNs) seek to mimic the spiking behavior of\nbiological neurons and are expected to play a key role in the advancement of\nneural computing and artificial intelligence. The efficiency of SNNs is often\ndetermined by the neural coding schemes. Existing coding schemes either cause\nhuge delays and energy consumption or necessitate intricate neuron models and\ntraining techniques. To address these issues, we propose a novel Stepwise\nWeighted Spike (SWS) coding scheme to enhance the encoding of information in\nspikes. This approach compresses the spikes by weighting the significance of\nthe spike in each step of neural computation, achieving high performance and\nlow energy consumption. A Ternary Self-Amplifying (TSA) neuron model with a\nsilent period is proposed for supporting SWS-based computing, aimed at\nminimizing the residual error resulting from stepwise weighting in neural\ncomputation. Our experimental results show that the SWS coding scheme\noutperforms the existing neural coding schemes in very deep SNNs, and\nsignificantly reduces operations and latency.","PeriodicalId":501347,"journal":{"name":"arXiv - CS - Neural and Evolutionary Computing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Stepwise Weighted Spike Coding for Deep Spiking Neural Networks\",\"authors\":\"Yiwen Gu, Junchuan Gu, Haibin Shen, Kejie Huang\",\"doi\":\"arxiv-2408.17245\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Spiking Neural Networks (SNNs) seek to mimic the spiking behavior of\\nbiological neurons and are expected to play a key role in the advancement of\\nneural computing and artificial intelligence. The efficiency of SNNs is often\\ndetermined by the neural coding schemes. Existing coding schemes either cause\\nhuge delays and energy consumption or necessitate intricate neuron models and\\ntraining techniques. To address these issues, we propose a novel Stepwise\\nWeighted Spike (SWS) coding scheme to enhance the encoding of information in\\nspikes. This approach compresses the spikes by weighting the significance of\\nthe spike in each step of neural computation, achieving high performance and\\nlow energy consumption. A Ternary Self-Amplifying (TSA) neuron model with a\\nsilent period is proposed for supporting SWS-based computing, aimed at\\nminimizing the residual error resulting from stepwise weighting in neural\\ncomputation. Our experimental results show that the SWS coding scheme\\noutperforms the existing neural coding schemes in very deep SNNs, and\\nsignificantly reduces operations and latency.\",\"PeriodicalId\":501347,\"journal\":{\"name\":\"arXiv - CS - Neural and Evolutionary Computing\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Neural and Evolutionary Computing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.17245\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Neural and Evolutionary Computing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.17245","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

尖峰神经网络(SNN)试图模仿生物神经元的尖峰行为,有望在神经计算和人工智能的发展中发挥关键作用。SNN 的效率通常由神经编码方案决定。现有的编码方案要么会造成巨大的延迟和能耗,要么需要复杂的神经元模型和训练技术。为了解决这些问题,我们提出了一种新颖的逐步加权尖峰(SWS)编码方案,以增强对信息尖峰的编码。这种方法通过在神经计算的每个步骤中对尖峰的重要性进行加权来压缩尖峰,从而实现高性能和低能耗。为支持基于 SWS 的计算,我们提出了一种具有无周期的三元自放大(TSA)神经元模型,旨在最大限度地减少神经计算中分步加权产生的残余误差。实验结果表明,在深度 SNN 中,SWS 编码方案优于现有的神经编码方案,并显著降低了运算量和延迟。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Stepwise Weighted Spike Coding for Deep Spiking Neural Networks
Spiking Neural Networks (SNNs) seek to mimic the spiking behavior of biological neurons and are expected to play a key role in the advancement of neural computing and artificial intelligence. The efficiency of SNNs is often determined by the neural coding schemes. Existing coding schemes either cause huge delays and energy consumption or necessitate intricate neuron models and training techniques. To address these issues, we propose a novel Stepwise Weighted Spike (SWS) coding scheme to enhance the encoding of information in spikes. This approach compresses the spikes by weighting the significance of the spike in each step of neural computation, achieving high performance and low energy consumption. A Ternary Self-Amplifying (TSA) neuron model with a silent period is proposed for supporting SWS-based computing, aimed at minimizing the residual error resulting from stepwise weighting in neural computation. Our experimental results show that the SWS coding scheme outperforms the existing neural coding schemes in very deep SNNs, and significantly reduces operations and latency.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Hardware-Friendly Implementation of Physical Reservoir Computing with CMOS-based Time-domain Analog Spiking Neurons Self-Contrastive Forward-Forward Algorithm Bio-Inspired Mamba: Temporal Locality and Bioplausible Learning in Selective State Space Models PReLU: Yet Another Single-Layer Solution to the XOR Problem Inferno: An Extensible Framework for Spiking Neural Networks
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1