AI Paper Atlas

Research map / Architectures and efficiency / Spiking networks

Exploring Loss Functions for Time-based Training Strategy in Spiking Neural Networks

Yaoyu Zhu, Wei Fang, Xiaodong Xie, Tiejun Huang, Zhaofei Yu

NeurIPS 2023 · Architectures and efficiency › Spiking networks · approach: Training deep spiking networks · 0 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
Replace counting (MSE) loss with enhanced counting loss, weight normalization (ablation)time-based SNN (EDBP baseline) · CIFAR-100top-1 accuracy: 63.98% -> 68.95%Improved
Replace counting (MSE) loss with enhanced counting loss, threshold normalization (ablation)time-based SNN · CIFAR-100top-1 accuracy: 66.35% -> 70.50%Improved
Replace weight normalization with threshold normalization, counting loss (ablation)time-based SNN · CIFAR-100top-1 accuracy: 63.98% -> 66.35%Improved
Replace weight normalization with threshold normalization, enhanced loss (ablation)time-based SNN · CIFAR-100top-1 accuracy: 68.95% -> 70.50%Improved
Use enhanced counting loss (ablation)time-based SNN · CIFAR-100gradient scale (L1 norm)Improved
Use threshold normalization (ablation)time-based SNN · CIFAR-100gradient scaleImproved
Use enhanced loss with threshold normalization (ablation)time-based SNN · CIFAR-100ratio of positive gradientsImproved
Use proposed method instead of EDBP with VGG11EDBP · CIFAR10top-1 accuracy: 92.10% -> 93.54%Improved
Use proposed method instead of EDBP with VGG11EDBP · CIFAR100top-1 accuracy: 63.97% -> 70.50%Improved
Use proposed method on saturated datasetTSSL-BP · MNISTtop-1 accuracy: 99.53% -> 99.50%No clear effect
Use proposed method instead of EDBPEDBP · Fashion-MNISTtop-1 accuracy: 93.28% -> 94.03%Improved
Use proposed method instead of EDBPEDBP · N-MNISTtop-1 accuracy: 99.39% -> 99.39%No 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