通过异质突触实现多时间尺度神经计算，提升脉冲网络性能与生物合理性。
HetSyn: Versatile Timescale Integration in Spiking Neural Networks via Heterogeneous Synapses
- 用突触特异性衰减常数建模异质突触，将时间整合从膜电位移至突触电流。
- 在语音、视觉识别等任务中显著提升性能，且噪声鲁棒性更强、记忆能力更优。
- 适合研究类脑计算、脉冲神经网络优化及生物机制启发的AI设计者。
脉冲神经网络（SNNs）为时序信息处理提供了生物合理且能效优越的框架。然而，现有研究忽视了生物神经元普遍存在的突触异质性这一基本特性，而该特性在时序处理与认知功能中起关键作用。为此，我们提出HetSyn，一种基于突触特异性时间常数的通用框架，将时间整合从膜电位转移到突触电流，实现灵活的多时间尺度整合，支持多样化的突触动力学。我们将其实现为HetSynLIF，即扩展的漏积分-放电（LIF）模型，具备突触级衰减动态。通过调整参数配置，HetSynLIF可退化为标准LIF、具有阈值适应的神经元或神经元层级异质模型。实验表明，HetSynLIF在模式生成、延迟匹配、语音识别和视觉识别等多种任务中均提升性能，同时展现出强噪声鲁棒性、优异工作记忆能力、有限神经元资源下的高效性以及跨时间尺度的泛化能力。对学习到的突触时间常数分析显示其趋势与生物突触观测一致。这些发现凸显了突触异质性在高效神经计算中的重要性，为类脑时序建模提供了新视角。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。