Research map / Architectures and efficiency / Spiking networks
TAB: Temporal Accumulated Batch Normalization in Spiking Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes Temporal Accumulated Batch Normalization (TAB), a batch normalization variant for directly training spiking neural networks that addresses temporal accumulation effects.
Problem
Directly training spiking neural networks is hard because of non-differentiable spiking activations and the temporally delayed accumulation of outputs over time, which complicates batch normalization.
Approach
Designs a batch normalization scheme that accounts for temporal accumulation of SNN outputs, so that normalization statistics are handled across time steps rather than per step alone (based on the abstract; details not fully available).
Experimental setup
Builds on: batch normalization
Closest papers by meaning
- Training High Performance Spiking Neural Network by Temporal Model Calibration (ICML 2025 · similarity 0.90)
- Temporal Flexibility in Spiking Neural Networks: Towards Generalization Across Time Steps and Deployment Friendliness (ICLR 2025 · similarity 0.89)
- TS-SNN: Temporal Shift Module for Spiking Neural Networks (ICML 2025 · similarity 0.89)
- Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings (ICLR 2024 · similarity 0.88)
- NDOT: Neuronal Dynamics-based Online Training for Spiking Neural Networks (ICML 2024 · similarity 0.87)
- Temporal Misalignment in ANN-SNN Conversion and its Mitigation via Probabilistic Spiking Neurons (ICML 2025 · similarity 0.87)
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.