用期望传播统一训练脉冲神经网络，无需梯度且更快收敛。
Training of Spiking Neural Networks with Expectation-Propagation
- 基于期望传播的消息传递框架，无须梯度即可训练SNN。
- 可同时学习参数边缘分布，处理隐藏层输出等干扰变量。
- 适用于确定性与随机脉冲网络，适合追求高效训练的开发者。
本文提出一种基于期望传播的统一消息传递框架，用于训练脉冲神经网络（SNNs）。该无梯度方法能够学习网络参数的边缘分布，并同时对隐藏层输出等干扰参数进行边缘化处理。该框架首次实现了使用批量训练样本对离散与连续权重、确定性与随机脉冲网络的联合训练。尽管理论上未保证收敛，但实际运行中收敛速度优于基于梯度的方法，且无需多次遍历训练数据。分类与回归结果为深度贝叶斯网络提供了新的高效训练路径。
原文摘要 · Abstract (English)
In this paper, we propose a unifying message-passing framework for training spiking neural networks (SNNs) using Expectation-Propagation. Our gradient-free method is capable of learning the marginal distributions of network parameters and simultaneously marginalizes nuisance parameters, such as the outputs of hidden layers. This framework allows for the first time, training of discrete and continuous weights, for deterministic and stochastic spiking networks, using batches of training samples. Although its convergence is not ensured, the algorithm converges in practice faster than gradient-based methods, without requiring a large number of passes through the training data. The classification and regression results presented pave the way for new efficient training methods for deep Bayesian networks.
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。