arXiv Machine Learning

Local Spike Timing Enables Gradient-based Learning in Neural Microcircuits

The paper introduces a new framework that reconciles discrete spike timing with continuous gradient-based learning in neural microcircuits (NMCs). By reformulating temporal credit assignment as a state‑separation problem, the authors develop a gradient‑tunneling (GT) algorithm and lead‑lag expansion technique that derive learning signals directly from local synaptic spike timing. Experiments show that GT‑trained NMCs achieve strong performance on long‑timescale evidence integration, noise‑robust memory retention, and real‑world benchmarks while using far fewer parameters than existing spiking neural network methods.

arXiv Machine Learning
Oct 9

Local Timescale Gates for Timescale-Robust Continual Spiking Neural Networks

Local Timescale Gating (LT‑Gate) is a neuron model that tracks fast and slow information in parallel and uses a learned gate to adjust their influence, enabling spiking neurons to preserve long‑term context while responding quickly. The approach includes a variance‑tracking regularization inspired by biological homeostasis and operates with local updates, making it compatible with neuromorphic hardware such as Intel’s Loihi chip. Empirical results show LT‑Gate improves accuracy and retention on sequential learning tasks, achieving about 51 % final accuracy versus 46 % for a recent Hebbian baseline and outperforming prior SNN methods.

By Devansh Deep, Ansh Tiwari, Ayush Chauhan
arXiv Computer Vision
Oct 16

The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks

The paper introduces the Dormant Spiking Neuron (DSN), a state-driven mechanism that allows neurons in spiking neural networks to enter a dormant state when their membrane potential falls below a negative threshold. This dynamic gating prunes redundant computations at the instance level and is trained end‑to‑end via backpropagation through time with surrogate gradients. Experiments on static and neuromorphic datasets, including ImageNet, show that DSN reduces computational energy by 40% to over 70% and improves baseline SNN accuracy by 1.34%, outperforming state‑of‑the‑art static pruning methods.

By Ruichen Ma, Yicai Chen, Pujun Zhou, Yue Zuo, Chongyang Li, Shuang Liu, Shaogang Hu, Guanchao Qiao
arXiv AI
Oct 2

SpikeMoE: Brain-Inspired Competitive Routing for Flexible Spiking Mixture-of-Experts

SpikeMoE introduces a spike-based k‑WTA router that uses lateral inhibition and refractory periods to select the top‑K experts based on discrete spike counts, inspired by hippocampal CA1 competition. The framework combines spiking neural network dynamics with mixture‑of‑experts conditional computation and adds a two‑stage missing‑modality module for robust multimodal processing. Experiments on vision, language, and multimodal tasks show that SpikeMoE matches or surpasses ANN baselines while offering energy‑efficient performance.

By Xiaoli Liu, Yujie Liang, Jialin Li, Malu Zhang
arXiv Machine Learning
Sep 15

Exploring napping paradigm for Recurrent Spiking Neural Networks

The paper proposes a biologically inspired micro‑sleep technique called napping for recurrent spiking neural networks, combining proportional weight scaling with continuous stochastic membrane activity. Experiments on an unsupervised SNN trained with trace‑based STDP on Gabor‑preprocessed MNIST show that well‑tuned napping can match the classification accuracy of conventional weight normalization while offering different clustering characteristics. The study suggests that napping may be preferable when representational structure is more important than raw classification speed, despite its higher simulation cost.

By Andreas Massey, Stefano Nichele, Aliaksandr Hubin
arXiv AI
Oct 19

SpikeQ: Spike-Guided Post-Training Quantization for Spiking Neural Networks

SpikeQ introduces a spike‑guided post‑training quantization framework for spiking neural networks, selecting weight levels by simulating downstream neurons to minimize spike errors and designing a reset‑aware grid for pre‑fire membrane potential quantization that avoids spike flips. The method outperforms existing grids on seven image‑processing benchmarks, maintaining full‑precision accuracy with 2‑bit pre‑fire potentials and staying within 2.59 points of full precision at 4 bits while drastically reducing memory and energy usage.

By Kai Sun, Peibo Duan, Zhanglu Yan, Guowei Zhang, Yongsheng Huang, Levin Kuhlmann