AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Reducing Information Loss for Spiking Neural Networks

Yufei Guo, Yuanpei Chen, Liwen Zhang, YingLei Wang, Xiaode Liu, Xinyi Tong, Yuanyuan Ou, Xuhui Huang, Zhe Ma

ECCV 2022 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks · 28 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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
replace hard-reset LIF with soft-reset IF (SRIF) (ablation)IF/LIF neuron, ResNet20 · CIFAR-10 (T=4)accuracy: 92.22% -> 92.46%Improved
replace hard-reset IF with soft-reset IF (SRIF) (ablation)ResNet20 · CIFAR-100 (T=4)accuracy: 66.95% -> 67.90%Improved
replace hard-reset IF with SRIF at 8 timesteps (ablation)ResNet20 · CIFAR-10 (T=8)accuracy: 92.86% -> 94.09%Improved
replace hard-reset IF with SRIF at 2 timesteps (ablation)ResNet20 · CIFAR-10 (T=2)accuracy: 90.07% -> 90.38%Improved
replace hard-reset LIF with SRIF at 8 timesteps (ablation)ResNet20 · CIFAR-100 (T=8)accuracy: 67.85% -> 69.90%Improved
use LIF instead of IF neuron (hard reset) (ablation)ResNet20 · CIFAR-100 (T=4)accuracy: 66.95% -> 66.00%Hurt
use LIF instead of IF neuron (hard reset) (ablation)ResNet20 · CIFAR-10 (T=4)accuracy: 92.04% -> 92.22%Improved
add MPR to SRIF (ablation)ResNet20 · CIFAR-100 (T=4)accuracy: 67.90% -> 70.63%Improved
add MPR to SRIF (ablation)ResNet20 · CIFAR-10 (T=4)accuracy: 92.46% -> 92.94%Improved
add MPR to SRIF (ablation)ResNet19 · CIFAR-10 (T=4)accuracy: 95.44% -> 96.27%Improved
add MPR to SRIF (ablation)ResNet19 · CIFAR-100 (T=4)accuracy: 77.85% -> 78.42%Improved
apply MPR to membrane potential (ablation)ResNet20 · CIFAR-10 (T=4)avg quantization error: 0.28 -> 0.04Improved

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