Theoretical Method for Solving BSS-ICA Using SVM

In this work we propose a new method for solving the blind source separation (BSS) problem using a support vector machine (SVM) workbench. Thus, we provide an introduction to SVM-ICA, a theoretical approach to unsupervised learning based on learning machines, which has frequently been proposed for classification and regression tasks. The key idea is to construct a Lagrange function from both the objective function and the corresponding constraints, by introducing a dual set of variables and solving the optimization problem. For this purpose we define a specific cost function and its derivative in terms of independence, i.e. inner products between the output and the objective function, transforming an unsupervised learning problem into a supervised learning machine task where optimization theory can be applied to develop effective algorithms.