Title :
Kernel exploratory projection pursuit
Author :
MacDonald, Donald ; Fyfe, Colin ; Charles, Darryl
Author_Institution :
Appl. Comput. Intelligence Res. Unit, Paisley Coll. of Technol., UK
Abstract :
Kernel methods are a recent innovation allowing one to perform efficient linear operations in a nonlinear space with the net effect of having nonlinear operations in data space. We derive three different methods of performing exploratory projection pursuit in kernel space and show on a standard data set that each gives interesting but different projections
Keywords :
unsupervised learning; kernel exploratory projection pursuit; linear operations; nonlinear space; Artificial intelligence; Computational intelligence; Covariance matrix; Eigenvalues and eigenfunctions; Equations; Kernel; Performance analysis; Principal component analysis; Technological innovation; Unsupervised learning;
Conference_Titel :
Knowledge-Based Intelligent Engineering Systems and Allied Technologies, 2000. Proceedings. Fourth International Conference on
Conference_Location :
Brighton
Print_ISBN :
0-7803-6400-7
DOI :
10.1109/KES.2000.885790
