Presentation	2007-03-14 Optimization of the parameters of Support Vector Machines' kernels using feed-forward neural networks Shin'ichi TAMURA,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	A novel approach to determining the optimal kernel parameters of Support Vector Machines is proposed. Based on the fact that a feed-forward neural network with infinitely many hidden units can realize any continuous mapping, an optimal mapping from the input space to a higher-dimensional space is estimated by neural network learning with a given learning input-output data. The kernel parameters of Support Vector Machines is determined using the criterion that the mapping determined implicitly by the kernel be as close as possible to the estimated mapping of a feed-forward neural network.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Feedforward neural network / Support Vector Machine / kernel
Paper #	NC2006-137
Date of Issue

Conference Information
Committee	NC
Conference Date	2007/3/7(1days)
Place (in Japanese)	(See Japanese page)
Place (in English)
Topics (in Japanese)	(See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To	Neurocomputing (NC)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Optimization of the parameters of Support Vector Machines' kernels using feed-forward neural networks
Sub Title (in English)
Keyword(1)	Feedforward neural network
Keyword(2)	Support Vector Machine
Keyword(3)	kernel
1st Author's Name	Shin'ichi TAMURA
1st Author's Affiliation	Research Laboratories, DENSO CORPORATION()
Date	2007-03-14
Paper #	NC2006-137
Volume (vol)	vol.106
Number (no)	588
Page	pp.pp.-
#Pages	6
Date of Issue