mlsanityData to 14 Oct 2026

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

arXiv 2508.11644 ↗First posted 1 Aug 2025q-bio.NC cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 67 references that are in the map. First posted on arXiv 1 Aug 2025.

Builds on

30 of 67 references.

References · 30

  1. 2019Surrogate Gradient Learning in Spiking Neural Networkscited by 626
  2. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 406
  3. 2020Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networkscited by 345
  4. 2021Deep Residual Learning in Spiking Neural Networkscited by 331
  5. 2015Unitary Evolution Recurrent Neural Networkscited by 294
  6. 2022Spikformer: When Spiking Neural Network Meets Transformercited by 271
  7. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 266
  8. 2018Going Deeper in Spiking Neural Networks: VGG and Residual Architecturescited by 245
  9. 2018Direct Training for Spiking Neural Networks: Faster, Larger, Bettercited by 233
  10. 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 181
  11. 2019Spiking-YOLO: Spiking Neural Network for Energy-Efficient Object Detectioncited by 177
  12. 2023Spike-driven Transformercited by 146
18 more
  1. 2020RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Networkcited by 145
  2. 2019The Heidelberg spiking datasets for the systematic evaluation of spiking neural networkscited by 137
  3. 2023Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networkscited by 122
  4. 2021A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibrationcited by 117
  5. 2021Accurate and efficient time-domain classification with adaptive spiking recurrent neural networkscited by 115
  6. 2024QKFormer: Hierarchical Spiking Transformer using Q-K Attentioncited by 49
  7. 2021Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium Statecited by 40
  8. 2020Surrogate gradients for analog neuromorphic computingcited by 38
  9. 2019Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networkscited by 32
  10. 2021A Long Short-Term Memory for AI Applications in Spike-based Neuromorphic Hardwarecited by 32
  11. 2018Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networkscited by 30
  12. 2020Brain-inspired global-local learning incorporated with neuromorphic computingcited by 28
  13. 2025Rethinking Spiking Neural Networks from an Ensemble Learning Perspectivecited by 12
  14. 2019An efficient and perceptually motivated auditory neural encoding and decoding algorithm for spiking neural networkscited by 9
  15. 2023Heterogeneous Neuronal and Synaptic Dynamics for Spike-Efficient Unsupervised Learning: Theory and Design Principlescited by 8
  16. 2017Bio-Inspired Multi-Layer Spiking Neural Network Extracts Discriminative Features from Speech Signalscited by 4
  17. 2020Skip-Connected Self-Recurrent Spiking Neural Networks with Joint Intrinsic Parameter and Synaptic Weight Trainingcited by 3
  18. 2021Composing Recurrent Spiking Neural Networks using Locally-Recurrent Motifs and Risk-Mitigating Architectural Optimizationcited by 2

Built on by

Not cited yet.