AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

AutoSNN: Towards Energy-Efficient Spiking Neural Networks

Byunggook Na, Jisoo Mok, Seongsik Park, Dongjin Lee, Hyeokjun Choe, Sungroh Yoon

ICML 2022 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks · 23 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 a spiking global average pooling layer (ablation)SNN_1 on CIFAR10 · CIFAR10accuracy: 86.93 -> 85.05Hurt
add a spiking global average pooling layer (ablation)SNN_1 on CIFAR10 · CIFAR10spikes: 154K -> 168KHurt
replace max pooling down-sampling with SCB_k3 blocks (ablation)SNN_1 on CIFAR10 · CIFAR10accuracy: 86.93 -> 87.94Improved
replace max pooling down-sampling with SCB_k3 blocks (ablation)SNN_1 on CIFAR10 · CIFAR10spikes: 154K -> 222KHurt
replace max pooling with average pooling for down-sampling (ablation)SNN_1 on CIFAR10 · CIFAR10accuracy: 86.93 -> 79.59Hurt
replace max pooling with average pooling for down-sampling (ablation)SNN_1 on CIFAR10 · CIFAR10spikes: 154K -> 293KHurt
increase the spike penalty in the fitness from lambda=0 to lambda=-0.08 (ablation)AutoSNN · CIFAR10spikes: 127K -> 108KImproved
increase the spike penalty in the fitness from lambda=0 to lambda=-0.08 (ablation)AutoSNN · CIFAR10accuracy: 88.69 -> 88.67No clear effect
replace evolutionary search with random search while retaining weight-sharing (ablation)AutoSNN · CIFAR10accuracy: 88.67 -> 88.10Hurt
search without spiking neurons, then add spiking neurons to the selected architecture (ablation)AutoSNN · CIFAR10accuracy: 88.69 -> 88.02Hurt
search without spiking neurons, then add spiking neurons to the selected architecture (ablation)AutoSNN · CIFAR10spikes: 127K -> 134KHurt
use an SIB_k3_e3 block instead of SCB_k3 in all TBD blocks (ablation)SNN_1 · CIFAR10accuracy: 86.93 -> 88.45Improved

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