TC-LIF: A Two-Compartment Spiking Neuron Model for Long-Term Sequential Modelling

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Shimin, Yang, Qu, Ma, Chenxiang, Wu, Jibin, Li, Haizhou, Tan, Kay Chen
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911778623979520
author Zhang, Shimin
Yang, Qu
Ma, Chenxiang
Wu, Jibin
Li, Haizhou
Tan, Kay Chen
author_facet Zhang, Shimin
Yang, Qu
Ma, Chenxiang
Wu, Jibin
Li, Haizhou
Tan, Kay Chen
contents The identification of sensory cues associated with potential opportunities and dangers is frequently complicated by unrelated events that separate useful cues by long delays. As a result, it remains a challenging task for state-of-the-art spiking neural networks (SNNs) to establish long-term temporal dependency between distant cues. To address this challenge, we propose a novel biologically inspired Two-Compartment Leaky Integrate-and-Fire spiking neuron model, dubbed TC-LIF. The proposed model incorporates carefully designed somatic and dendritic compartments that are tailored to facilitate learning long-term temporal dependencies. Furthermore, a theoretical analysis is provided to validate the effectiveness of TC-LIF in propagating error gradients over an extended temporal duration. Our experimental results, on a diverse range of temporal classification tasks, demonstrate superior temporal classification capability, rapid training convergence, and high energy efficiency of the proposed TC-LIF model. Therefore, this work opens up a myriad of opportunities for solving challenging temporal processing tasks on emerging neuromorphic computing systems. Our code is publicly available at https://github.com/ZhangShimin1/TC-LIF.
format Preprint
id arxiv_https___arxiv_org_abs_2308_13250
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle TC-LIF: A Two-Compartment Spiking Neuron Model for Long-Term Sequential Modelling
Zhang, Shimin
Yang, Qu
Ma, Chenxiang
Wu, Jibin
Li, Haizhou
Tan, Kay Chen
Neural and Evolutionary Computing
The identification of sensory cues associated with potential opportunities and dangers is frequently complicated by unrelated events that separate useful cues by long delays. As a result, it remains a challenging task for state-of-the-art spiking neural networks (SNNs) to establish long-term temporal dependency between distant cues. To address this challenge, we propose a novel biologically inspired Two-Compartment Leaky Integrate-and-Fire spiking neuron model, dubbed TC-LIF. The proposed model incorporates carefully designed somatic and dendritic compartments that are tailored to facilitate learning long-term temporal dependencies. Furthermore, a theoretical analysis is provided to validate the effectiveness of TC-LIF in propagating error gradients over an extended temporal duration. Our experimental results, on a diverse range of temporal classification tasks, demonstrate superior temporal classification capability, rapid training convergence, and high energy efficiency of the proposed TC-LIF model. Therefore, this work opens up a myriad of opportunities for solving challenging temporal processing tasks on emerging neuromorphic computing systems. Our code is publicly available at https://github.com/ZhangShimin1/TC-LIF.
title TC-LIF: A Two-Compartment Spiking Neuron Model for Long-Term Sequential Modelling
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2308.13250