AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Reconstructing Spiking Neural Networks Using a Single Neuron with Autapses

Wuque Cai, Hongze Sun, Quan Tang, Shifeng Mao, Zhenxing Wang, Jiayi He, Duo Chen, Dezhong Yao, Daqing Guo

CVPR 2026 · Architectures and efficiency › Spiking networks · approach: Spiking transformers · 0 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 standard SNN reservoir with TDA-SNN at small size (16 nodes) (ablation)TDA-SNN · DEAPaccuracy (%): 81.21 -> 77.59Hurt
scale reservoir to 256 nodes with TDA-SNN vs STD-SNN (ablation)TDA-SNN · DEAPaccuracy (%): 79.92 -> 88.65Improved
scale reservoir to 256 nodes with TDA-SNN vs STD-SNN (ablation)TDA-SNN · SHDaccuracy (%): 77.63 -> 80.04Improved
increase SHD reservoir from 128 to 256 nodes (ablation)TDA-SNN · SHDaccuracy (%): 80.68 -> 80.04Hurt
max-connection delay selection at 2 delays vs random delay (ablation)TDA-SNN RC · SHDaccuracy (%): 78.62 -> 72.09Hurt
increase number of autapse delays 1 to 64 (random delay) (ablation)TDA-SNN MLP · MNISTaccuracy (%): 84.03 -> 96.42Improved
random delay vs max-connection selection with many delays (ablation)TDA-SNN MLP · MNISTaccuracy (%): 94.38 -> 96.42Improved
random delay vs max-connection selection with many delays (ablation)TDA-SNN RC · DEAPaccuracy (%): 84.47 vs 84.47 at 64 delaysNo clear effect
increase MLP depth 1 to 4 layers (ablation)TDA-SNN MLP · MNISTaccuracy (%): 94.41 -> 95.60Improved
increase MLP depth 1 to 4 layers (ablation)TDA-SNN MLP · fMNISTaccuracy (%): 86.62 -> 87.12 then decreasesMixed
increase MLP nodes from 16 to 256 (ablation)TDA-SNN MLP · DVS Gestureaccuracy (%): 53.99 -> 72.95Improved
use TDA-SNN single-neuron convolution instead of standard SNN convTDA-SNN · CIFAR-10accuracy (%): 47.31 -> 37.64Hurt

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