提出固定点并行训练法，让脉冲神经网络训练时间恒定
Efficient Parallel Training Methods for Spiking Neural Networks with Constant Time Complexity
- 用固定点迭代重构脉冲神经元，实现全时步并行计算
- 时间复杂度从O(T)降至O(K)，K=3时提速超10倍
- 无需改架构，适合长时序任务的高效训练
脉冲神经网络（SNN）因需逐个处理T个脉冲，常面临O(T)的时间复杂度，导致训练成本高昂。本文提出一种无需修改网络结构或引入额外假设的固定点并行训练（FPT）方法，通过将漏电积分-放电（LIF）神经元表示为固定点迭代形式，使所有T个时间步可并行处理，将时间复杂度降低至O(K)，其中K为小常数（通常K=3）。我们提供了FPT的理论收敛性分析，并证明现有并行脉冲神经元可视为本方法的特例。实验表明，FPT能有效模拟原始LIF神经元动态，在不损失精度的前提下显著减少计算时间，为实际应用特别是长期任务提供可扩展、高效的解决方案。代码将于https://github.com/WanjinVon/FPT公开。
原文摘要 · Abstract (English)
Spiking Neural Networks (SNNs) often suffer from high time complexity $O(T)$ due to the sequential processing of $T$ spikes, making training computationally expensive. In this paper, we propose a novel Fixed-point Parallel Training (FPT) method to accelerate SNN training without modifying the network architecture or introducing additional assumptions. FPT reduces the time complexity to $O(K)$, where $K$ is a small constant (usually $K=3$), by using a fixed-point iteration form of Leaky Integrate-and-Fire (LIF) neurons for all $T$ timesteps. We provide a theoretical convergence analysis of FPT and demonstrate that existing parallel spiking neurons can be viewed as special cases of our proposed method. Experimental results show that FPT effectively simulates the dynamics of original LIF neurons, significantly reducing computational time without sacrificing accuracy. This makes FPT a scalable and efficient solution for real-world applications, particularly for long-term tasks. Our code will be released at \href{https://github.com/WanjinVon/FPT}{\texttt{https://github.com/WanjinVon/FPT}}.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。