Attention Spiking Neural Networks

尖峰神经网络 计算机科学 人工智能 杠杆(统计) 块(置换群论) 模式识别(心理学) MNIST数据库 人工神经网络 机器学习 几何学 数学
作者
Man Yao,Guangshe Zhao,Hengyu Zhang,Yifan Hu,Lei Deng,Yonghong Tian,Bo Xu,Guoqi Li
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [IEEE Computer Society]
卷期号:45 (8): 9393-9410 被引量:65
标识
DOI:10.1109/tpami.2023.3241201
摘要

Brain-inspired spiking neural networks (SNNs) are becoming a promising energy-efficient alternative to traditional artificial neural networks (ANNs). However, the performance gap between SNNs and ANNs has been a significant hindrance to deploying SNNs ubiquitously. To leverage the full potential of SNNs, in this paper we study the attention mechanisms, which can help human focus on important information. We present our idea of attention in SNNs with a multi-dimensional attention module, which infers attention weights along the temporal, channel, as well as spatial dimension separately or simultaneously. Based on the existing neuroscience theories, we exploit the attention weights to optimize membrane potentials, which in turn regulate the spiking response. Extensive experimental results on event-based action recognition and image classification datasets demonstrate that attention facilitates vanilla SNNs to achieve sparser spiking firing, better performance, and energy efficiency concurrently. In particular, we achieve top-1 accuracy of 75.92% and 77.08% on ImageNet-1 K with single/4-step Res-SNN-104, which are state-of-the-art results in SNNs. Compared with counterpart Res-ANN-104, the performance gap becomes -0.95/+0.21 percent and the energy efficiency is 31.8×/7.4×. To analyze the effectiveness of attention SNNs, we theoretically prove that the spiking degradation or the gradient vanishing, which usually holds in general SNNs, can be resolved by introducing the block dynamical isometry theory. We also analyze the efficiency of attention SNNs based on our proposed spiking response visualization method. Our work lights up SNN's potential as a general backbone to support various applications in the field of SNN research, with a great balance between effectiveness and energy efficiency.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
728完成签到,获得积分10
3秒前
xiaofeng5838完成签到,获得积分10
3秒前
ronnie完成签到,获得积分10
3秒前
6秒前
寒冷芷蕊完成签到,获得积分20
6秒前
6秒前
Jane完成签到,获得积分10
6秒前
一氧化二氢完成签到,获得积分10
12秒前
凡事发生必有利于我完成签到,获得积分10
13秒前
yihaiqin完成签到 ,获得积分10
17秒前
轩辕剑身完成签到,获得积分0
17秒前
coolkid完成签到 ,获得积分0
18秒前
你怎么那么美完成签到,获得积分10
18秒前
游艺完成签到 ,获得积分10
21秒前
冬月完成签到 ,获得积分10
21秒前
薛乎虚完成签到 ,获得积分10
22秒前
23秒前
大胖完成签到,获得积分10
23秒前
野火197完成签到,获得积分10
27秒前
28秒前
量子星尘发布了新的文献求助10
31秒前
April完成签到,获得积分10
31秒前
周舟完成签到 ,获得积分10
34秒前
V_I_G完成签到 ,获得积分10
35秒前
nick完成签到,获得积分10
36秒前
高高高完成签到 ,获得积分10
39秒前
彪壮的亦瑶完成签到 ,获得积分10
40秒前
科研通AI2S应助科研通管家采纳,获得10
42秒前
Perry应助科研通管家采纳,获得60
42秒前
Akim应助科研通管家采纳,获得10
42秒前
鱼雷完成签到,获得积分10
43秒前
廿伊发布了新的文献求助10
45秒前
我是125完成签到,获得积分10
47秒前
依人如梦完成签到 ,获得积分10
48秒前
49秒前
PDIF-CN2完成签到,获得积分10
53秒前
雪雪完成签到 ,获得积分10
54秒前
55秒前
Willow完成签到,获得积分10
58秒前
研研研完成签到,获得积分10
59秒前
高分求助中
【提示信息,请勿应助】关于scihub 10000
Les Mantodea de Guyane: Insecta, Polyneoptera [The Mantids of French Guiana] 3000
徐淮辽南地区新元古代叠层石及生物地层 3000
The Mother of All Tableaux: Order, Equivalence, and Geometry in the Large-scale Structure of Optimality Theory 3000
Handbook of Industrial Diamonds.Vol2 1100
Global Eyelash Assessment scale (GEA) 1000
Picture Books with Same-sex Parented Families: Unintentional Censorship 550
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4038157
求助须知:如何正确求助?哪些是违规求助? 3575869
关于积分的说明 11373842
捐赠科研通 3305650
什么是DOI,文献DOI怎么找? 1819255
邀请新用户注册赠送积分活动 892655
科研通“疑难数据库(出版商)”最低求助积分说明 815022