Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation
Author:
Affiliation:
1. The Chinese University of Hong Kong,Shenzhen
2. School of Artificial Intelligence, Peking University,Key Lab. of Machine Perception (MoE)
3. Center for Data Science, Peking University
Funder
National Natural Science Foundation of China
Publisher
IEEE
Link
http://xplorestaging.ieee.org/ielx7/9878378/9878366/09878999.pdf?arnumber=9878999
Reference54 articles.
1. Going Deeper in Spiking Neural Networks: VGG and Residual Architectures
2. Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification
3. Surrogate Gradient Learning in Spiking Neural Networks: Bringing the Power of Gradient-Based Optimization to Spiking Neural Networks
4. Supervised Learning Based on Temporal Coding in Spiking Neural Networks
5. A million spiking-neuron integrated circuit with a scalable communication network and interface
Cited by 54 articles. 订阅此论文施引文献 订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. STCSNN: High energy efficiency spike-train level spiking neural networks with spatio-temporal conversion;Neurocomputing;2024-11
2. Directly training temporal Spiking Neural Network with sparse surrogate gradient;Neural Networks;2024-11
3. Self-architectural knowledge distillation for spiking neural networks;Neural Networks;2024-10
4. Converting Artificial Neural Networks to Ultralow-Latency Spiking Neural Networks for Action Recognition;IEEE Transactions on Cognitive and Developmental Systems;2024-08
5. Energy efficient and low-latency spiking neural networks on embedded microcontrollers through spiking activity tuning;Neural Computing and Applications;2024-08-01
1.学者识别学者识别
2.学术分析学术分析
3.人才评估人才评估
"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370
www.globalauthorid.com
TOP
Copyright © 2019-2024 北京同舟云网络信息技术有限公司 京公网安备11010802033243号 京ICP备18003416号-3