Deep-RLS: A Model-Inspired Deep Learning Approach to Nonlinear PCA
This work addresses blind source separation, a key problem in signal processing, but appears incremental as it builds on existing deep unfolding and RLS methods.
The authors tackled the problem of nonlinear principal component analysis for blind source separation by proposing Deep-RLS, a model-inspired deep learning approach that unfolds recursive least squares iterations into a neural network, resulting in significantly improved accuracy in recovering source signals compared to traditional RLS.
In this work, we consider the application of model-based deep learning in nonlinear principal component analysis (PCA). Inspired by the deep unfolding methodology, we propose a task-based deep learning approach, referred to as Deep-RLS, that unfolds the iterations of the well-known recursive least squares (RLS) algorithm into the layers of a deep neural network in order to perform nonlinear PCA. In particular, we formulate the nonlinear PCA for the blind source separation (BSS) problem and show through numerical analysis that Deep-RLS results in a significant improvement in the accuracy of recovering the source signals in BSS when compared to the traditional RLS algorithm.