Effective Blind Source Separation Based on the Adam Algorithm
Abstract
In this paper, we derive a modified InfoMax algorithm for the solution of Blind Signal Separation (BSS) problems by using advanced stochastic methods. The proposed approach is based on a novel stochastic optimization approach known as the Adaptive Moment Estimation (Adam) algorithm. The proposed BSS solution can benefit from the excellent properties of the Adam approach. In order to derive the new learning rule, the Adam algorithm is introduced in the derivation of the cost function maximization in the standard InfoMax algorithm. The natural gradient adaptation is also considered. Finally, some experimental results show the effectiveness of the proposed approach.
Keywords
Cite
@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}
}
Comments
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