paper-with-me

홈 › Papers

ParaRevSNN: A Parallel Reversible Spiking Neural Network for Efficient Training and Inference

2025-08-02 · Changqing Xu, Guoqing Sun, Yi Liu, Xinfang Liao, Yintang Yang arxiv

Reversible Spiking Neural Networks (RevSNNs) enable memory-efficient training by reconstructing forward activations during backpropagation, but suffer from high latency due to strictly sequential computation. To overcome this limitation, we propose ParaRevSNN, a parallel reversible SNN architecture that decouples sequential dependencies between reversible blocks while preserving reversibility. This design enables inter-block parallelism, significantly accelerating training and inference while retaining the memory-saving benefits of reversibility. Experiments on CIFAR10, CIFAR100, CIFAR10-DVS, and DVS128 Gesture demonstrate that ParaRevSNN matches or exceeds the accuracy of standard RevSNNs, while reducing training time by up to 35.2\% and inference time to 18.15\%, making it well-suited for deployment in resource-constrained scenarios.

📄 PDF Abstract BibTeX arXiv:2508.01223

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

High-Performance Temporal Reversible Spiking Neural Networks with $O(L)$ Training Memory and $O(1)$ Inference Cost

2024-05-26 · Jiakui Hu, Man Yao, Xuerui Qiu, Yuhong Chou 외

Multi-timestep simulation of brain-inspired Spiking Neural Networks (SNNs) boost memory requirements during training and increase inference energy cost. Current training methods cannot simultaneously solve both training …

Memory-Efficient Reversible Spiking Neural Networks

2023-12-13 · Hong Zhang, Yu Zhang

Spiking neural networks (SNNs) are potential competitors to artificial neural networks (ANNs) due to their high energy-efficiency on neuromorphic hardware. However, SNNs are unfolded over simulation time steps during the…

GPU

Parallel Training in Spiking Neural Networks

2026-02-01 · Yanbin Huang, Man Yao, Yuqi Pan, Changze Lv 외 arxiv

The bio-inspired integrate-fire-reset mechanism of spiking neurons constitutes the foundation for efficient processing in Spiking Neural Networks (SNNs). Recent progress in large models demands that spiking neurons suppo…

Reinforcement LearningImage Classification

Towards Zero Memory Footprint Spiking Neural Network Training

2023-08-16 · Bin Lei, Sheng Lin, Pei-Hung Lin, Chunhua Liao 외

Biologically-inspired Spiking Neural Networks (SNNs), processing information using discrete-time events known as spikes rather than continuous values, have garnered significant attention due to their hardware-friendly an…

PaReprop: Fast Parallelized Reversible Backpropagation

2023-06-15 · Tyler Zhu, Karttikeya Mangalam

The growing size of datasets and deep learning models has made faster and memory-efficient training crucial. Reversible transformers have recently been introduced as an exciting new method for extremely memory-efficient …

Benchmarking