AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Cannistraci-Hebb Training on Ultra-Sparse Spiking Neural Networks

Yuan Hua, Jilin Zhang, Yingtao Zhang, Leyi You, Baobo Xiong, Carlo Vittorio Cannistraci, Hong Chen

ICLR 2026 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks · 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
CH-SNN vs SD-SNN/DPAP/Grad R at higher link sparsity6Conv 2FC / 2FC · MNIST, CIFAR-10link sparsity: MNIST 2FC 77.36% (DPAP) -> 97.75%Improved
CH-SNN vs SD-SNN accuracy on CIFAR-1006Conv 2FC · CIFAR-100accuracy: 75.33% -> 75.22%No clear effect
CH-SNN vs SD-SNN and Grad R on DVS-Gesture2Conv 2FC · DVS-Gestureaccuracy: 96.21% -> 95.45% (SD-SNN)Hurt
CH-SNN sparse network vs fully connected on S-TPS-TP 3FC · DVS-Gestureaccuracy: 89.02% -> 91.29%Improved
CH-SNN sparse network vs fully connected on S-TPS-TP 3FC · N-MNISTaccuracy: 96.38% -> 96.20%Hurt
CH-SNN sparse network vs fully connected on S-TPS-TP 3FC · DVS-Gestureenergy: 78mJ -> 0.8mJImproved
add SSCTI (spike-correlated topological initialization) (ablation)CH-SNN · CIFAR-10 99% sparsityaccuracy: 10.00% -> 34.55%Improved
add SSWI (sparse spike weight initialization) (ablation)CH-SNN · CIFAR-10 99% sparsityaccuracy: 10.00% -> 77.40%Improved
add both SSCTI and SSWI (ablation)CH-SNN · MNIST 99% sparsityaccuracy: 9.80% -> 96.88%Improved
vary batch size (ablation)CH-SNN · sensitivity analysisaccuracyNo clear effect

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