Publication:
Learning non-linear time scales with Kernel γ-Filters

Loading...
Thumbnail Image
Identifiers
Publication date
2009-01
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Elsevier
Impact
Google Scholar
Export
Research Projects
Organizational Units
Journal Issue
Abstract
A family of kernel methods, based on the γ-filter structure, is presented for non-linear system identification and time series prediction. The kernel trick allows us to develop the natural non-linear extension of the (linear) support vector machine (SVM) γ-filter, but this approach yields a rigid system model without non-linear cross relation between time-scales. Several functional analysis properties allow us to develop a full, principled family of kernel γ-filters. The improved performance in several application examples suggests that a more appropriate representation of signal states is achieved.
Description
Keywords
Gamma-Filters, Support vector machines, Mercer's Kernel, Nonlinear System Identification
Bibliographic citation
Neurocomputing, Jan 2009, Vol. 72, Issues 4-6, pp.1324-1328