Evolving Sum and Composite Kernel Functions for Regularization Networks

0359155 - ÚI 2012 RIV DE eng C - Conference Paper (international conference)
Vidnerová, Petra - Neruda, Roman
Evolving Sum and Composite Kernel Functions for Regularization Networks.
Adaptive and Natural Computing Algorithms. Part I. Vol. 1. Heidelberg: Springer, 2011 - (Dobnikar, A.; Lotrič, U.; Šter, B.), s. 180-189. Lecture Notes in Computer Science, 6593. ISBN 978-3-642-20281-0. ISSN 0302-9743.
[ICANNGA'2011. International Conference /10./. Ljubljana (SI), 14.04.2011-16.04.2011]
R&D Projects: GA MŠMT OC10047; GA AV ČR KJB100300804
Institutional research plan: CEZ:AV0Z10300504
Keywords : regularization networks * kernel functions * genetic algorithms
Subject RIV: IN - Informatics, Computer Science

In this paper we propose a novel evolutionary algorithm for regularization networks. The main drawback of regularization networks in practical applications is the presence of meta-parameters, including the type and parameters of kernel functions Our learning algorithm provides a solution to this problem by searching through a space of different kernel functions, including sum and composite kernels. Thus, an optimal combination of kernel functions with parameters is evolved for given task specified by training data. Comparisons of composite kernels, single kernels, and traditional Gaussians are provided in several experiments.
Permanent Link: http://hdl.handle.net/11104/0196991