Some Comparisons of Networks with Radial and Kernel Units

0379010 - ÚI 2013 RIV DE eng C - Conference Paper (international conference)
Kůrková, Věra
Some Comparisons of Networks with Radial and Kernel Units.
Artificial Neural Networks and Machine Learning – ICANN 2012. Berlin: Springer, 2012 - (Villa, A.; Duch, W.; Érdi, P.; Masulli, F.; Palm, G.), s. 17-24. Lecture Notes in Computer Science, 7553. ISBN 978-3-642-33265-4. ISSN 0302-9743.
[ICANN 2012. International Conference on Artificial Neural Networks /22./. Lausanne (CH), 11.09.2012-14.09.2012]
R&D Projects: GA ČR GAP202/11/1368
Institutional support: RVO:67985807
Keywords : radial and kernel networks * universal approximation property * fixed and varying widths * minimization of error functionals * stabilizers induced by kernels
Subject RIV: IN - Informatics, Computer Science

Two types of computational models, radial-basis function networks with units having varying widths and kernel networks where all units have a fixed width, are investigated in the framework of scaled kernels. The impact of widths of kernels on approximation of multivariable functions, generalization modelled by regularization with kernel stabilizers, and minimization of error functionals is analyzed.
Permanent Link: http://hdl.handle.net/11104/0210297