清晨好,您是今天最早来到科研通的研友!由于当前在线用户较少,发布求助请尽量完整地填写文献信息,科研通机器人24小时在线,伴您科研之路漫漫前行!

LIAF-Net: Leaky Integrate and Analog Fire Network for Lightweight and Efficient Spatiotemporal Information Processing

计算机科学 信息处理 分布式计算 计算机网络 生物 神经科学
作者
Zhenzhi Wu,Hehui Zhang,Yihan Lin,Guoqi Li,Meng Wang,Ye Tang
出处
期刊:IEEE transactions on neural networks and learning systems [Institute of Electrical and Electronics Engineers]
卷期号:33 (11): 6249-6262 被引量:75
标识
DOI:10.1109/tnnls.2021.3073016
摘要

Spiking neural networks (SNNs) based on Leaky Integrate and Fire (LIF) model have been applied to energy-efficient temporal and spatiotemporal processing tasks. Thanks to the bio-plausible neuronal dynamics and simplicity, LIF-SNN benefits from event-driven processing, however, usually faces the embarrassment of reduced performance. This may because in LIF-SNN the neurons transmit information via spikes. To address this issue, in this work, we propose a Leaky Integrate and Analog Fire (LIAF) neuron model, so that analog values can be transmitted among neurons, and a deep network termed as LIAF-Net is built on it for efficient spatiotemporal processing. In the temporal domain, LIAF follows the traditional LIF dynamics to maintain its temporal processing capability. In the spatial domain, LIAF is able to integrate spatial information through convolutional integration or fully-connected integration. As a spatiotemporal layer, LIAF can also be used with traditional artificial neural network (ANN) layers jointly. Experiment results indicate that LIAF-Net achieves comparable performance to Gated Recurrent Unit (GRU) and Long short-term memory (LSTM) on bAbI Question Answering (QA) tasks, and achieves state-of-the-art performance on spatiotemporal Dynamic Vision Sensor (DVS) datasets, including MNIST-DVS, CIFAR10-DVS and DVS128 Gesture, with much less number of synaptic weights and computational overhead compared with traditional networks built by LSTM, GRU, Convolutional LSTM (ConvLSTM) or 3D convolution (Conv3D). Compared with traditional LIF-SNN, LIAF-Net also shows dramatic accuracy gain on all these experiments. In conclusion, LIAF-Net provides a framework combining the advantages of both ANNs and SNNs for lightweight and efficient spatiotemporal information processing.

科研通智能强力驱动
Strongly Powered by AbleSci AI
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
2秒前
小清完成签到,获得积分10
11秒前
Aaron完成签到,获得积分10
30秒前
35秒前
42秒前
桐桐的应助被葛力采纳,获得10
50秒前
脑洞疼的应助被矢思然采纳,获得10
50秒前
1分钟前
李爱国的应助被搞怪的方盒采纳,获得30
1分钟前
1分钟前
1分钟前
1分钟前
1分钟前
烟花的应助被开朗的尔蝶采纳,获得10
1分钟前
1分钟前
1分钟前
1分钟前
幸福丹蝶完成签到,获得积分10
1分钟前
1分钟前
1分钟前
2分钟前
叫啥好呢完成签到 ,获得积分10
2分钟前
clairewen完成签到,获得积分10
2分钟前
2分钟前
2分钟前
3分钟前
3分钟前
3分钟前
矢思然发布了新的文献求助10
3分钟前
3分钟前
葛力发布了新的文献求助10
3分钟前
3分钟前
3分钟前
3分钟前
3分钟前
4分钟前
4分钟前
NN的应助被萧雨墨采纳,获得10
4分钟前
123完成签到 ,获得积分10
4分钟前
4分钟前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 2000
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
基于界面调控的高效湿气发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8190190
求助须知:如何正确求助?哪些是违规求助? 9577282
关于积分的说明 21852326
捐赠科研通 7788645
什么是DOI,文献DOI怎么找? 3436298
关于科研通互助平台的介绍 2560076
邀请新用户注册赠送积分活动 2482902