arXiv Machine Learning By Xiangnan Zhang, Jingxin Liu, Ranqi Lu, Jingyu Liu, Qunxi Dong, Fuze Tian, Lixian Zhu, Bin Hu, Bj\"orn W. Schuller

Local Spike Timing Enables Gradient-based Learning in Neural Microcircuits

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

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