AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Adaptive Smoothing Gradient Learning for Spiking Neural Networks

Ziming Wang, Runhao Jiang, Shuang Lian, Rui Yan, Huajin Tang

ICML 2023 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
adaptive (learnable) smoothing width with dual-mode forwarding instead of constant surrogate width (ablation)SNN trained on CIFAR-10/CIFAR-100 (ResNet-19/ResNet-18) · CIFAR-10 and CIFAR-100 ablationaccuracy (%): CIFAR-10 width 10.0: 30.85 to 93.53; CIFAR-100 width 1.0: 65.19 to 76.09Improved
adaptive width learning (vs fixed width) under full-spike and p=0.8 noise (ablation)ResNet-19 on CIFAR-10, 2 steps · CIFAR-10 ablation (Table 3)accuracy (%): up to about +1 point at p=1.0 and p=0.8 across widthsImproved
dual-mode switching (noise probability p=0.8 instead of full spikes p=1.0) (ablation)ResNet-19 on CIFAR-10 with adaptive width · CIFAR-10, 2 stepsaccuracy (%): 92.94 to 93.32Improved
noise probability p set too low or too high (fixed p sweep) (ablation)ResNet-19 on CIFAR-10 · CIFAR-10 noise probability analysistest accuracyMixed
ASGL training instead of surrogate gradient learning on SHD recurrent SNN700-240-20 recurrent SNN · SHDaccuracy (%): 86.9 vs 84.8 for EventProp (best baseline listed)Improved
ASGL training on DVS-CIFAR10 with VGGSNNVGGSNN · DVS-CIFAR10accuracy: 84.50 vs 83.17 for TETImproved
ASGL training on Tiny-ImageNet with VGG-13 at 8 time stepsVGG-13 · Tiny-ImageNetaccuracy (%): 56.81 vs 55.37 for offline LTLImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy