HetSyn: Versatile Timescale Integration in Spiking Neural Networks via Heterogeneous Synapses

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Deng, Zhichao, Liu, Zhikun, Wang, Junxue, Chen, Shengqian, Wei, Xiang, Yu, Qiang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909738366664704
author Deng, Zhichao
Liu, Zhikun
Wang, Junxue
Chen, Shengqian
Wei, Xiang
Yu, Qiang
author_facet Deng, Zhichao
Liu, Zhikun
Wang, Junxue
Chen, Shengqian
Wei, Xiang
Yu, Qiang
contents Spiking Neural Networks (SNNs) offer a biologically plausible and energy-efficient framework for temporal information processing. However, existing studies overlook a fundamental property widely observed in biological neurons-synaptic heterogeneity, which plays a crucial role in temporal processing and cognitive capabilities. To bridge this gap, we introduce HetSyn, a generalized framework that models synaptic heterogeneity with synapse-specific time constants. This design shifts temporal integration from the membrane potential to the synaptic current, enabling versatile timescale integration and allowing the model to capture diverse synaptic dynamics. We implement HetSyn as HetSynLIF, an extended form of the leaky integrate-and-fire (LIF) model equipped with synapse-specific decay dynamics. By adjusting the parameter configuration, HetSynLIF can be specialized into vanilla LIF neurons, neurons with threshold adaptation, and neuron-level heterogeneous models. We demonstrate that HetSynLIF not only improves the performance of SNNs across a variety of tasks-including pattern generation, delayed match-to-sample, speech recognition, and visual recognition-but also exhibits strong robustness to noise, enhanced working memory performance, efficiency under limited neuron resources, and generalization across timescales. In addition, analysis of the learned synaptic time constants reveals trends consistent with empirical observations in biological synapses. These findings underscore the significance of synaptic heterogeneity in enabling efficient neural computation, offering new insights into brain-inspired temporal modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2508_11644
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HetSyn: Versatile Timescale Integration in Spiking Neural Networks via Heterogeneous Synapses
Deng, Zhichao
Liu, Zhikun
Wang, Junxue
Chen, Shengqian
Wei, Xiang
Yu, Qiang
Neurons and Cognition
Machine Learning
Spiking Neural Networks (SNNs) offer a biologically plausible and energy-efficient framework for temporal information processing. However, existing studies overlook a fundamental property widely observed in biological neurons-synaptic heterogeneity, which plays a crucial role in temporal processing and cognitive capabilities. To bridge this gap, we introduce HetSyn, a generalized framework that models synaptic heterogeneity with synapse-specific time constants. This design shifts temporal integration from the membrane potential to the synaptic current, enabling versatile timescale integration and allowing the model to capture diverse synaptic dynamics. We implement HetSyn as HetSynLIF, an extended form of the leaky integrate-and-fire (LIF) model equipped with synapse-specific decay dynamics. By adjusting the parameter configuration, HetSynLIF can be specialized into vanilla LIF neurons, neurons with threshold adaptation, and neuron-level heterogeneous models. We demonstrate that HetSynLIF not only improves the performance of SNNs across a variety of tasks-including pattern generation, delayed match-to-sample, speech recognition, and visual recognition-but also exhibits strong robustness to noise, enhanced working memory performance, efficiency under limited neuron resources, and generalization across timescales. In addition, analysis of the learned synaptic time constants reveals trends consistent with empirical observations in biological synapses. These findings underscore the significance of synaptic heterogeneity in enabling efficient neural computation, offering new insights into brain-inspired temporal modeling.
title HetSyn: Versatile Timescale Integration in Spiking Neural Networks via Heterogeneous Synapses
topic Neurons and Cognition
Machine Learning
url https://arxiv.org/abs/2508.11644