Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chen, Hanqi, Yu, Lixing, Zhan, Shaojie, Yao, Penghui, Shao, Jiankun
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2409.04978
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917880596004864
author Chen, Hanqi
Yu, Lixing
Zhan, Shaojie
Yao, Penghui
Shao, Jiankun
author_facet Chen, Hanqi
Yu, Lixing
Zhan, Shaojie
Yao, Penghui
Shao, Jiankun
contents The computational inefficiency of spiking neural networks (SNNs) is primarily due to the sequential updates of membrane potential, which becomes more pronounced during extended encoding periods compared to artificial neural networks (ANNs). This highlights the need to parallelize SNN computations effectively to leverage available hardware parallelism. To address this, we propose Membrane Potential Estimation Parallel Spiking Neurons (MPE-PSN), a parallel computation method for spiking neurons that enhances computational efficiency by enabling parallel processing while preserving the intrinsic dynamic characteristics of SNNs. Our approach exhibits promise for enhancing computational efficiency, particularly under conditions of elevated neuron density. Empirical experiments demonstrate that our method achieves state-of-the-art (SOTA) accuracy and efficiency on neuromorphic datasets. Codes are available at~\url{https://github.com/chrazqee/MPE-PSN}. \end{abstract}
format Preprint
id arxiv_https___arxiv_org_abs_2409_04978
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Time-independent Spiking Neuron via Membrane Potential Estimation for Efficient Spiking Neural Networks
Chen, Hanqi
Yu, Lixing
Zhan, Shaojie
Yao, Penghui
Shao, Jiankun
Computer Vision and Pattern Recognition
The computational inefficiency of spiking neural networks (SNNs) is primarily due to the sequential updates of membrane potential, which becomes more pronounced during extended encoding periods compared to artificial neural networks (ANNs). This highlights the need to parallelize SNN computations effectively to leverage available hardware parallelism. To address this, we propose Membrane Potential Estimation Parallel Spiking Neurons (MPE-PSN), a parallel computation method for spiking neurons that enhances computational efficiency by enabling parallel processing while preserving the intrinsic dynamic characteristics of SNNs. Our approach exhibits promise for enhancing computational efficiency, particularly under conditions of elevated neuron density. Empirical experiments demonstrate that our method achieves state-of-the-art (SOTA) accuracy and efficiency on neuromorphic datasets. Codes are available at~\url{https://github.com/chrazqee/MPE-PSN}. \end{abstract}
title Time-independent Spiking Neuron via Membrane Potential Estimation for Efficient Spiking Neural Networks
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.04978