Title :
ICA by mutual information minimization: An approach for avoiding local minima
Author :
Babaie-Zadeh, Massoud ; Bahmani, Bahman ; Jutten, Christian
Author_Institution :
Electr. Eng. Dept., Sharif Univ. of Technol., Tehran, Iran
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.
Keywords :
blind source separation; gradient methods; independent component analysis; BSS; ICA; MI minimization; blind source separation; gradient descent approaches; mutual information minimization; Abstracts; Estimation;
Conference_Titel :
Signal Processing Conference, 2005 13th European
Conference_Location :
Antalya
Print_ISBN :
978-160-4238-21-1
