Efficient Structure Slimming for Spiking Neural Networks

Yaxin Li, Xuanye Fang, Yuyuan Gao, Dongdong Zhou, Jiangrong Shen, Jian K. Liu, Gang Pan, Qi Xu*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

59 Downloads (Pure)

Abstract

Spiking neural networks (SNNs) are deeply inspired by biological neural information systems. Compared to convolutional neural networks (CNNs), SNNs are low power consumption because of their spike based information processing mechanism. However, most of the current structures of SNNs are fully-connected or converted from deep CNNs which poses redundancy connections. While the structure and topology in human brain systems are sparse and efficient. This paper aims at taking full advantage of sparse structure and low power consumption which lie in human brain and proposed efficient structure slimming methods. Inspired by the development of biological neural network structures, this paper designed types of structure slimming methods including neuron pruning and channel pruning. In addition to pruning, this paper also considers the growth and development of the nervous system. Through iterative application of the proposed neural pruning and rewiring algorithms, experimental evaluations on CIFAR-10, CIFAR-100, and DVS-Gesture datasets demonstrate the effectiveness of the structure slimming methods. When the parameter count is reduced to only about 10% of the original, the performance decreases by less than 1%.
Original languageEnglish
Article number10391076
Number of pages9
JournalIEEE Transactions on Artificial Intelligence
Early online date11 Jan 2024
DOIs
Publication statusE-pub ahead of print - 11 Jan 2024

Bibliographical note

Funding:
This work is supported by National Natural Science Foundation of China (NSFC No.62206037, 62306274), The Open Project of Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, No. MMC202104, Open Research Fund from Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), under Grant No. GMLKF-22-11 and the Fundamental Research Funds for the Central Universities (DUT21RC(3)091)

Fingerprint

Dive into the research topics of 'Efficient Structure Slimming for Spiking Neural Networks'. Together they form a unique fingerprint.

Cite this