CASIA OpenIR  > 国家专用集成电路设计工程技术研究中心
Fast and Efficient Deep Sparse Multi-Strength Spiking Neural Networks with Dynamic Pruning
Chen RZ(陈睿智)1,2; Ma H(马鸿)1; Xie SL(谢少林)1; Guo P(郭鹏)1,2; Li P(李品)1; Wang DL(王东琳)1
Conference Name2018 International Joint Conference on Neural Networks (IJCNN)
Conference Date2018-7
Conference Place巴西里约热内卢

Deep convolutional neural networks (CNNs) have shown state-of-the-art accuracy for various computer vision and speech tasks. However, CNNs are computation-intensive and energy-inefficient which are difficult to be deployed in real-time systems. Event-driven Spiking Neural Networks (SNNs) are extremely power efficient, which provides an alternative for ultra-low power applications. But effective training methods for SNN are still lacking. Due to its spatio-temporal feature of SNN, conventional training method for CNN can not be employed in SNN. To address this problem, some researchers proposed to convert the corresponding weights of trained CNNs into the synapse weights of SNNs (CNNs-SNNs). Nevertheless, limited by the [0,1] constraints on the SNN neuron outputs, the accuracy of the converted SNNs is impaired. Besides, as the SNN network becomes deeper, the convergence speed of SNN inference are unacceptably slow. In this work, we proposed an innovative deep multi-strength SNN (M-SNN) structure which relaxes the restriction of the neuron output spike strength while the event-driven feature for low-power implementations is maintained. Using this architecture, large scale SNN can be converted from CNN with comparable accuracy and fast inference speed. The evaluation results show 3.7x convergence speedup. Moreover, with multi-strength spike, aggressive pruning strategies can be applied to reduce the computational operations by almost 85% while maintaining the same accuracy.

Indexed ByEI
Document Type会议论文
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Chen RZ,Ma H,Xie SL,et al. Fast and Efficient Deep Sparse Multi-Strength Spiking Neural Networks with Dynamic Pruning[C],2018.
Files in This Item: Download All
File Name/Size DocType Version Access License
paper2.pdf(5380KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Chen RZ(陈睿智)]'s Articles
[Ma H(马鸿)]'s Articles
[Xie SL(谢少林)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Chen RZ(陈睿智)]'s Articles
[Ma H(马鸿)]'s Articles
[Xie SL(谢少林)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Chen RZ(陈睿智)]'s Articles
[Ma H(马鸿)]'s Articles
[Xie SL(谢少林)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: paper2.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.