Stability analysis of complex ICA by negentropy maximization: A unique perspective

详细信息    查看全文

• 作者：Guobing Qian^a ; ^b ; ^{shuaiguobing@hotmail.com" class="auth_mail" title="E-mail the corresponding author}Author Vitae ; Ping Wei^bAuthor Vitae
• 关键词：CMN ; Unstable area ; Undesirable solutions
• 刊名：Neurocomputing
• 出版年：2016
• 出版时间：19 November 2016
• 年：2016
• 卷：214
• 期：Complete
• 页码：80-85
• 全文大小：581 K

文摘

This letter investigates the stability analysis of complex ICA by Negentropy Maximization. Based on the theoretical analysis for the fixed-point iteration and cost function of Quasi-Newton CMN (N-CMN) algorithm, we have found that (1) the unstable area does not have any influence on the performance of the N-CMN algorithm and (2) the algorithm may converge to an undesirable solution even if the sources satisfy the stable conditions.