
Proceedings Paper
Auxiliary function approach to independent component analysis and independent vector analysisFormat | Member Price | Non-Member Price |
---|---|---|
$17.00 | $21.00 |
Paper Abstract
In this paper, we review an auxiliary function approach to independent component analysis (ICA) and independent vector analysis (IVA). The derived algorithm consists of two alternative updates: 1) weighted covariance matrix update and 2) demixing matrix update, which include no tuning parameters such as a step size in the gradient descent method. The monotonic decrease of the objective function is guaranteed by the principle of the auxiliary function method. The experimental evaluation shows that the derived update rules yield faster convergence and better results than natural gradient updates. An efficient implementation on a mobile phone is also presented.
Paper Details
Date Published: 11 June 2015
PDF: 12 pages
Proc. SPIE 9496, Independent Component Analyses, Compressive Sampling, Large Data Analyses (LDA), Neural Networks, Biosystems, and Nanoengineering XIII, 94960L (11 June 2015); doi: 10.1117/12.2179859
Published in SPIE Proceedings Vol. 9496:
Independent Component Analyses, Compressive Sampling, Large Data Analyses (LDA), Neural Networks, Biosystems, and Nanoengineering XIII
Harold H. Szu; Liyi Dai; Yufeng Zheng, Editor(s)
PDF: 12 pages
Proc. SPIE 9496, Independent Component Analyses, Compressive Sampling, Large Data Analyses (LDA), Neural Networks, Biosystems, and Nanoengineering XIII, 94960L (11 June 2015); doi: 10.1117/12.2179859
Show Author Affiliations
N. Ono, National Institute of Informatics (Japan)
Published in SPIE Proceedings Vol. 9496:
Independent Component Analyses, Compressive Sampling, Large Data Analyses (LDA), Neural Networks, Biosystems, and Nanoengineering XIII
Harold H. Szu; Liyi Dai; Yufeng Zheng, Editor(s)
© SPIE. Terms of Use
