20804384

Source:http://linkedlifedata.com/resource/pubmed/id/20804384

Download in:

Switch to

Custom View

Named Graph Language Inference

Statements in which the resource exists as a subject.
Predicate	Object
rdf:type	pubmed:Citation
lifeskim:mentions	umls-concept:C0023185, umls-concept:C0033213, umls-concept:C1194380, umls-concept:C1881303
pubmed:issue	11
pubmed:dateCreated	2010-10-13
pubmed:abstractText	We develop a novel generalization bound for learning the kernel problem. First, we show that the generalization analysis of the kernel learning problem reduces to investigation of the suprema of the Rademacher chaos process of order 2 over candidate kernels, which we refer to as Rademacher chaos complexity. Next, we show how to estimate the empirical Rademacher chaos complexity by well-established metric entropy integrals and pseudo-dimension of the set of candidate kernels. Our new methodology mainly depends on the principal theory of U-processes and entropy integrals. Finally, we establish satisfactory excess generalization bounds and misclassification error rates for learning gaussian kernels and general radial basis kernels.
pubmed:language	eng
pubmed:journal	http://linkedlifedata.com/resource/pubmed/journal/9426182
pubmed:citationSubset	IM
pubmed:status	MEDLINE
pubmed:month	Nov
pubmed:issn	1530-888X
pubmed:author	pubmed-author:CampbellColinC, pubmed-author:YingYimingY
pubmed:issnType	Electronic
pubmed:volume	22
pubmed:owner	NLM
pubmed:authorsComplete	Y
pubmed:pagination	2858-86
pubmed:meshHeading	pubmed-meshheading:20804384-Algorithms, pubmed-meshheading:20804384-Learning, pubmed-meshheading:20804384-Neural Networks (Computer)
pubmed:year	2010
pubmed:articleTitle	Rademacher chaos complexities for learning the kernel problem.
pubmed:affiliation	College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, U.K. mathying@gmail.com
pubmed:publicationType	Journal Article