AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Deep Spiking Neural Network: Energy Efficiency Through Time based Coding

Bing Han, Kaushik Roy

ECCV 2020 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks · 161 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
use TSC time-based coding instead of RMP rate codingANN-SNN conversion, ResNet-20 · CIFAR-10accuracy loss: 0.11% -> 0.05%Improved
use TSC time-based coding instead of RMP rate codingANN-SNN conversion, ResNet-20 · CIFAR-100accuracy loss: 0.9% -> 0.54%Improved
use TSC time-based coding instead of RMP rate codingANN-SNN conversion, VGG-16 · CIFAR-100accuracy loss: 0.29% -> 0.25%Improved
use TSC time-based coding instead of RMP rate codingANN-SNN conversion, ResNet-34 · ImageNetaccuracy loss: 0.75% -> 0.71%Improved
use TSC time-based coding instead of RMP rate codingANN-SNN conversion, VGG-16 · ImageNetaccuracy loss: 0.4% -> 0.03%Improved
use TSC time-based coding instead of RMP rate codingANN-SNN conversion, VGG-16 · CIFAR-10accuracy loss: < 0.01% -> < 0.01%No clear effect
use TSC coding instead of RMP-SNNVGG-16 SNN · CIFAR-10inference latency to reach accuracy: about 200 time-steps -> 64 time-stepsImproved
use TSC coding instead of IF-neuron SNNVGG-16 SNN · CIFAR-10inference latency to reach accuracy: about 640 time-steps -> 64 time-stepsImproved
use TSC coding instead of RMP-SNNVGG-16 SNN · CIFAR-10spike rate: 66.3 times lowerImproved
use TSC coding instead of IF-neuron SNNVGG-16 SNN · CIFAR-10spike rate: 20.3 times lowerImproved
scale firing threshold by 0.8 down to 0.6 of Vin_max (ablation)ResNet-20 TSC-SNN · CIFAR-10accuracy and latency: 91.36%Improved
scale firing threshold down to 0.2 of Vin_max (ablation)ResNet-20 TSC-SNN · CIFAR-10accuracyHurt

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