基于 Adam 算法的有效盲源分离
机器学习
2026-01-13 v2
摘要
本文通过使用先进的随机方法，推导出一种用于解决盲信号分离（BSS）问题的改进 InfoMax 算法。所提方法基于一种称为自适应矩估计（Adam）算法的新型随机优化方法。所提出的 BSS 解决方案能够受益于 Adam 方法的优良特性。为推导新的学习规则，在标准 InfoMax 算法的代价函数最大化推导中引入了 Adam 算法。同时也考虑了自然梯度自适应。最后，一些实验结果展示了所提方法的有效性。
引用
@article{arxiv.1605.07833,
title = {Effective Blind Source Separation Based on the Adam Algorithm},
author = {Michele Scarpiniti and Simone Scardapane and Danilo Comminiello and Raffaele Parisi and Aurelio Uncini},
journal= {arXiv preprint arXiv:1605.07833},
year = {2026}
}
备注
Revised version after review process. This paper has been presented at the 26-th Italian Workshop on Neural Networks (WIRN2016) May 18-20, Vietri sul Mare, Salerno, Italy. It will be published soon as a chapter in a book of the the Springer Smart Innovation, Systems and Technologies series