Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Shuo, Liu, Boxiao, Liu, Zeshi, You, Haihang
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916489588637696
author Chen, Shuo
Liu, Boxiao
Liu, Zeshi
You, Haihang
author_facet Chen, Shuo
Liu, Boxiao
Liu, Zeshi
You, Haihang
contents Spiking Neural Networks (SNNs) have gained significant attention due to the energy-efficient and multiplication-free characteristics. Despite these advantages, deploying large-scale SNNs on edge hardware is challenging due to limited resource availability. Network pruning offers a viable approach to compress the network scale and reduce hardware resource requirements for model deployment. However, existing SNN pruning methods cause high pruning costs and performance loss because they lack efficiency in processing the sparse spike representation of SNNs. In this paper, inspired by the critical brain hypothesis in neuroscience and the high biological plausibility of SNNs, we explore and leverage criticality to facilitate efficient pruning in deep SNNs. We firstly explain criticality in SNNs from the perspective of maximizing feature information entropy. Second, We propose a low-cost metric for assess neuron criticality in feature transmission and design a pruning-regeneration method that incorporates this criticality into the pruning process. Experimental results demonstrate that our method achieves higher performance than the current state-of-the-art (SOTA) method with up to 95.26\% reduction of pruning cost. The criticality-based regeneration process efficiently selects potential structures and facilitates consistent feature representation.
format Preprint
id arxiv_https___arxiv_org_abs_2311_16141
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks
Chen, Shuo
Liu, Boxiao
Liu, Zeshi
You, Haihang
Neural and Evolutionary Computing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Spiking Neural Networks (SNNs) have gained significant attention due to the energy-efficient and multiplication-free characteristics. Despite these advantages, deploying large-scale SNNs on edge hardware is challenging due to limited resource availability. Network pruning offers a viable approach to compress the network scale and reduce hardware resource requirements for model deployment. However, existing SNN pruning methods cause high pruning costs and performance loss because they lack efficiency in processing the sparse spike representation of SNNs. In this paper, inspired by the critical brain hypothesis in neuroscience and the high biological plausibility of SNNs, we explore and leverage criticality to facilitate efficient pruning in deep SNNs. We firstly explain criticality in SNNs from the perspective of maximizing feature information entropy. Second, We propose a low-cost metric for assess neuron criticality in feature transmission and design a pruning-regeneration method that incorporates this criticality into the pruning process. Experimental results demonstrate that our method achieves higher performance than the current state-of-the-art (SOTA) method with up to 95.26\% reduction of pruning cost. The criticality-based regeneration process efficiently selects potential structures and facilitates consistent feature representation.
title Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks
topic Neural and Evolutionary Computing
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2311.16141