AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Progressive Tandem Learning for Pattern Recognition With Deep Spiking Neural Networks

Jibin Wu, Chenglin Xu, Xiao Jing Han, Daquan Zhou, Malu Zhang, Haizhou Li, Kay Chen Tan

TPAMI 2021 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks · 154 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
train SNN with progressive tandem learning instead of ANNAlexNet · Cifar-10accuracy: 89.59 -> 90.86Improved
train SNN with progressive tandem learning instead of ANNVGG-11 · Cifar-10accuracy: 90.59 -> 91.24Improved
convert to SNN with progressive tandem learning instead of ANNAlexNet · ImageNet-12top-1 accuracy: 58.53 -> 55.19Hurt
convert to SNN with progressive tandem learning instead of ANNVGG-16 · ImageNet-12top-1 accuracy: 71.65 -> 65.08Hurt
use progressive tandem learning instead of constrain-then-train (16 vs 200 time steps)AlexNet SNN · ImageNet-12top-1 accuracy: 51.80 -> 55.19Improved
reduce weight precision from Float32 to 4-bit (ablation)SNN · Cifar-10accuracy: 90.33 -> 89.48Hurt
reduce weight precision from Float32 to 4-bit (ablation)SNN · MNISTaccuracy: 99.32 -> 99.29No clear effect
enlarge encoding time window from 16 to 32 (ablation)SNN autoencoder · MNIST reconstructionMSE: 0.01720 -> 0.00662Improved
enlarge encoding time window from 1 to 16 (ablation)SNN autoencoder · MNIST reconstructionMSE: 0.04032 -> 0.01720Improved
convert ANN separator to SNNspeech separation · WSJ0-2mix open conditionSI-SDR (dB): 12.8 -> 12.2Hurt
convert ANN separator to SNNspeech separation · WSJ0-2mix open conditionPESQ: 2.94 -> 2.85No clear effect
use SNN with patience period of only 1 in adaptive scheduler (ablation)PTL training · Cifar-10accuracyNo 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