Kawanabe, M. and Theis, Fabian J. (2006) Estimating Non-Gaussian Subspaces by Characteristic Functions. In: Rosca, J., (ed.) Independent Component Analysis and Blind Signal Separation, 6th International Conference, ICA 2006, Charleston, SC, USA, March 5-8, 2006. Proceedings. Lecture notes in computer science, 3889. Springer, Berlin, pp. 157-164. ISBN 3-540-32630-8 (print), 978-3-540-32630-4 (e-book).
Full text not available from this repository.
In this article, we consider high-dimensional data which contains a low-dimensional non-Gaussian structure contaminated with Gaussian noise and propose a new method to identify the non-Gaussian subspace. A linear dimension reduction algorithm based on the fourth-order cumulant tensor was proposed in our previous work . Although it works well for sub-Gaussian structures, the performance is not satisfactory for super-Gaussian data due to outliers. To overcome this problem, we construct an alternative by using Hessian of characteristic functions which was applied to (multidimensional) independent component analysis [10,11]. A numerical study demonstrates the validity of our method.
|Item Type:||Book Section|
|Institutions:||Biology, Preclinical Medicine > Institut für Biophysik und physikalische Biochemie > Prof. Dr. Elmar Lang|
|Subjects:||500 Science > 570 Life sciences|
|Created at the University of Regensburg:||Unknown|
|Deposited On:||01 Oct 2010 07:58|
|Last Modified:||01 Oct 2010 07:58|