AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks

Shikuang Deng, Shi Gu

ICLR 2021 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks · 99 citations (OpenAlex)

Read the paper

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 threshold ReLU rather than regular ReLU in the source ANN (ablation)ANN-to-SNN conversion · CIFAR-10, CIFAR-Net; simulation length 400-600accuracy: 90.16±0.03 -> 90.61±0.01Improved
Use threshold ReLU rather than regular ReLU in the source ANN (ablation)ANN-to-SNN conversion · CIFAR-100, ResNet-20; simulation length 400-600accuracy: 66.74±0.04 -> 69.82±0.03Improved
Add shift to threshold ReLU (ablation)ANN-to-SNN conversion · CIFAR-10, CIFAR-Net; simulation length 400-600accuracy: 90.61±0.01 -> 90.37±0.02Hurt
Add shift to threshold ReLU (ablation)ANN-to-SNN conversion · CIFAR-10, VGG-16; simulation length 400-600accuracy: 92.26±0.01 -> 92.26±0.01No clear effect
Add shift to threshold ReLU (ablation)ANN-to-SNN conversion · CIFAR-100, ResNet-20; simulation length 400-600accuracy: 69.82±0.03 -> 69.81±0.02No clear effect
Combine threshold ReLU with shift instead of using threshold alone (ablation)ANN-to-SNN conversion · CIFAR-100, VGG-16; simulation length 128conversion loss: 0.21%(0.08%) -> 0.15%(0.02%)Improved
Combine threshold ReLU with shift instead of using threshold alone (ablation)ANN-to-SNN conversion · CIFAR-10, ResNet-20; simulation length 32conversion loss: 19.72%(21.01%) -> -0.98%(0.31%)Improved
Apply threshold ReLU plus shift instead of regular ReLUANN-to-SNN conversion · CIFAR-10, VGG-16; simulation length 32conversion loss: RMP: 33.33%; Our Work-TS: -0.2%(0.05%)Improved
Apply threshold ReLU plus shift instead of regular ReLUANN-to-SNN conversion · CIFAR-100, ResNet-20; simulation length 32conversion loss: RMP: 41.08%; Our Work-TS: -1.32%(1.4%)Improved
Use threshold ReLU rather than regular ReLU in the source RNN (ablation)RNN-to-SNN conversion · Movie Reviews validation setaccuracy: 0.5100 -> 0.5430Improved
Convert the threshold-ReLU RNN rather than directly train an SNN with surrogate gradientSentiment analysis SNN · Movie Reviews validation setaccuracy: 0.5106 -> 0.5430Improved
Use threshold ReLU and shift rather than threshold ReLU alone (ablation)ANN-to-SNN conversion · ResNet-20, CIFAR-100; simulation length 16conversion loss: 3.35%(6.07%) -> -1.32%(1.40%)Improved

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