新的SNN训练和剪枝方法提升效率和性能

报道来源 [4]

1. arXiv cs.LG TIER_1 English(EN) · Muhammad Hamza · 2026-07-01 04:00

   面向高能效脉冲神经网络的临界约束迭代剪枝方法：结合重要性评分

   arXiv:2606.30676v1 Announce Type: cross Abstract: Deploying spiking neural networks (SNNs) on neuromorphic hardware demands aggressive synaptic pruning while preserving temporal computation integrity. Existing strategies either neglect neuronal criticality or rely on convex relax…

2. arXiv cs.AI TIER_1 English(EN) · Himanshu Udupi, Xiaocong Yang, ChengXiang Zhai · 2026-06-30 04:00

   Globally Optimal Training of Spiking Neural Networks via Parameter Reconstruction

   arXiv:2605.08022v2 Announce Type: replace-cross Abstract: Spiking Neural Networks (SNNs) have been proposed as biologically plausible and energy-efficient alternatives to conventional Artificial Neural Networks (ANNs). However, the training of SNN usually relies on surrogate grad…

3. arXiv cs.NE (Neural & Evolutionary) TIER_1 English(EN) · Muhammad Hamza · 2026-06-26 08:48

   面向高能效脉冲神经网络的临界约束迭代剪枝方法：结合重要性评分

   Deploying spiking neural networks (SNNs) on neuromorphic hardware demands aggressive synaptic pruning while preserving temporal computation integrity. Existing strategies either neglect neuronal criticality or rely on convex relaxations of the inherently combinatorial pruning pro…

4. arXiv cs.CV TIER_1 English(EN) · Shaogang Hu · 2026-06-30 14:07

   内在稳定的脉冲神经网络：在无批归一化的情况下克服性能障碍

   The performance of deep spiking neural networks (SNNs) often relies on batch normalization (BN). However, the advanced dynamic BN variants used in state-of-the-art models introduce runtime multiplications, which weaken the hardware-efficiency motivation of SNNs. To address this t…