ICA BY MUTUAL INFORMATION MINIMIZATION: AN APPROACH FOR AVOIDING LOCAL MINIMA (TueAmOR11)

Author(s) : Massoud Babaie-Zadeh (Sharif University of Technology, Iran) Bahman Bahmani (Sharif University of Technology, Iran) Christian Jutten (LIS, INPG, France)

Abstract : Using Mutual Information (MI) minimization is very common in Blind Source Separation (BSS). However, it is known that gradient descent approaches may trap in local minima of MI in constrained models. In this paper, it is proposed that this problem may be solved using a `poor' estimation of the derivative of MI.

Menu