AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

EICIL: Joint Excitatory Inhibitory Cycle Iteration Learning for Deep Spiking Neural Networks

Zihang Shao, Xuanye Fang, Yaxin Li, Chaoran Feng, Jiangrong Shen, Qi Xu

NeurIPS 2023 · Architectures and efficiency › Spiking networks · approach: Sparse efficient spiking sequence models · 1 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
add GSI cycle iteration (GS + STDP-BW) instead of GS onlySpiking ResNet18 · CIFAR100test accuracy (%): 56.28 -> 63.03Improved
add GSGI cycle iteration (GS + STDP-BW-GS) instead of GS onlySpiking ResNet18 · CIFAR100test accuracy (%): 56.28 -> 63.47Improved
add GSGI instead of GS onlySpiking ResNet18 · CIFAR10test accuracy (%): 89.39 -> 90.34Improved
add GSGI instead of GS onlySpiking VGG11 · CIFAR10test accuracy (%): 83.96 -> 85.31Improved
add GSGI instead of GS onlySpiking VGG11 · CIFAR100test accuracy (%): 54.01 -> 55.71Improved
add GSGI instead of GS onlySpiking VGG11 · MNISTtest accuracy (%): 98.2 -> 98.77Improved
add GSGI instead of GS onlyExcitatory inhibition Net · CIFAR100test accuracy (%): 53.61 -> 53.86Improved
add GSGI instead of GS onlyExcitatory inhibition Net · MNISTtest accuracy (%): 99.33 -> 99.35No clear effect
replace GS with STDP-BW (backprop added to multi-layer STDP) (ablation)Spiking ResNet18 · CIFAR10test accuracy (%): 89.39 -> 90.39Improved
replace GS with STDP-BW (ablation)Spiking ResNet18 · CIFAR100test accuracy (%): 56.28 -> 56.20No clear effect
replace GS with STDP-BW-GS (ablation)Spiking VGG11 · MNISTtest accuracy (%): 98.2 -> 95.85Hurt
use STDP-BW-GS instead of STDP-BW in the cycle iteration (GSGI vs GSI) (ablation)Spiking ResNet18 · CIFAR10test accuracy (%): 90.05 -> 90.34Improved

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