提出随机平衡传播框架，实现高效生物可解释的脉冲神经网络训练。
StochEP: Stochastic Equilibrium Propagation for Spiking Convergent Recurrent Neural Networks
- 引入随机脉冲神经元，使平衡传播更适配生物脉冲机制。
- 在视觉任务上逼近传统反向传播性能，且支持深层网络训练。
- 适合类脑计算与芯片级学习，兼顾效率与生物学合理性。
脉冲神经网络（SNN）具备节能、稀疏、类生物计算的潜力。尽管通过时间反向传播（BPTT）和替代梯度可实现强性能，但其生物合理性不足。平衡传播（EP）提供了更局部、更符合生物原理的替代方案。然而，现有基于确定性神经元的EP框架要么需复杂机制处理脉冲动态中的不连续性，要么无法扩展到复杂视觉任务。受生物脉冲机制的随机性及近期硬件趋势启发，我们提出一种将概率脉冲神经元融入EP范式的随机EP框架。该方法平滑优化过程，稳定训练，并支持深层卷积脉冲收敛递归神经网络（CRNN）的可扩展学习。理论证明表明，在均场理论下，所提随机EP动力学可近似确定性EP，从而继承其理论保障。该框架在视觉基准测试中缩小了与BPTT训练的SNN及非脉冲CRNN的差距，同时保持局部性，凸显随机EP在类脑与片上学习中的前景。
原文摘要 · Abstract (English)
Spiking Neural Networks (SNNs) promise energy-efficient, sparse, biologically inspired computation. Training them with Backpropagation Through Time (BPTT) and surrogate gradients achieves strong performance but remains biologically implausible. Equilibrium Propagation (EP) provides a more local and biologically grounded alternative. However, existing EP frameworks, primarily based on deterministic neurons, either require complex mechanisms to handle discontinuities in spiking dynamics or fail to scale beyond simple visual tasks. Inspired by the stochastic nature of biological spiking mechanism and recent hardware trends, we propose a stochastic EP framework that integrates probabilistic spiking neurons into the EP paradigm. This formulation smoothens the optimization landscape, stabilizes training, and enables scalable learning in deep convolutional spiking convergent recurrent neural networks (CRNNs). We provide theoretical guarantees showing that the proposed stochastic EP dynamics approximate deterministic EP under mean-field theory, thereby inheriting its underlying theoretical guarantees. The proposed framework narrows the gap to both BPTT-trained SNNs and EP-trained non-spiking CRNNs in vision benchmarks while preserving locality, highlighting stochastic EP as a promising direction for neuromorphic and on-chip learning.
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。