arXiv Machine Learning

Activation-Energy Pruning for Spiking Neural Networks: Unsupervised Personalization via Spike-Count Saliency

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 Machine Learning
Oct 9

DADP: Dynamic Activity-Dependent Pruning, A Reverse Hebbian-Inspired Structural Pruning Method

The paper introduces Dynamic Activity-Dependent Pruning (DADP), a biologically inspired pruning technique that uses accumulated pre‑synaptic activations and post‑synaptic error gradients to assess connection importance. Unlike traditional methods that rely on fixed layer budgets or magnitude thresholds, DADP employs a single global threshold, allowing it to dynamically allocate sparsity across a network’s depth and prune neurons and channels during training. Experiments on MLP, VGG‑16, ResNet‑18, BiLSTM‑CRF, and MiniBERT show that DADP matches or surpasses existing pruning methods, achieving 73.67% accuracy at 99% sparsity on ResNet‑18 while preserving feature diversity as measured by Shannon entropy and effective rank.

By Bhushan Deshpande
arXiv AI
Jun 12

Structured vs. Unstructured Pruning: An Exponential Gap

arXiv:2603. 02234v3 Announce Type: replace-cross Abstract: The Strong Lottery Ticket Hypothesis (SLTH) states that large, randomly initialized neural networks contain sparse subnetworks capable of approximating a target function at initialization without training, suggesting that pruning alone is sufficient.

By Davide Ferre' (CNRS, COATI, UniCA, I3S), Fr\'ed\'eric Giroire (I3S, COATI, UniCA), Frederik Mallmann-Trenn (CNRS, COATI, I3S, UniCA), Emanuele Natale (CNRS, COATI, I3S, UniCA)
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 12

Convex Optimization of Spiking Neural Networks with Global and Approximation Guarantees

The paper presents a convex formulation for training spiking neural networks (SNNs), showing that the weight‑decay‑regularized training problem for a class of threshold RNNs—including leaky integrate‑and‑fire SNNs—has zero duality gap and matches a convex program’s optimal value. To handle the exponential size of the resulting convex programs, the authors introduce a randomized surrogate with a high‑probability approximation guarantee. Empirical results demonstrate that the convex variant outperforms surrogate‑gradient training on addition and first‑last‑XOR tasks, matches performance on sequential MNIST, and falls slightly behind a reservoir baseline on base‑3 and base‑5 addition.

By Himanshu Udupi, Calvin Ang, Sungyoon Kim, Xiaocong Yang, ChengXiang Zhai
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