Publication:
Learning the value of a function by using hypercircle inequality for data error

dc.contributor.authorB. Novaprateepen_US
dc.contributor.authorK. Khompurngsonen_US
dc.contributor.authorD. Poltemen_US
dc.contributor.otherMahidol Universityen_US
dc.contributor.otherUniversity of Phayaoen_US
dc.date.accessioned2018-05-03T08:09:28Z
dc.date.available2018-05-03T08:09:28Z
dc.date.issued2011-01-06en_US
dc.description.abstractIn this paper, we briefly review Hypercircle inequality for data error (Hide) measured with square loss. We provide it in the case that the unit ball B is replaced by δB where δ is any positive number. Moreover, we also discuss some important facts of Hide for practical computation and study the problem in learning the value of a function in reproducing kernel Hilbert space (RKHS) by using the available material from Hide with different values of δ We compare our numerical experiment to the method of regularization, which is the standard method for learning problem.en_US
dc.identifier.citationInternational Journal of Mathematics and Computers in Simulation. Vol.5, No.1 (2011), 1-8en_US
dc.identifier.issn19980159en_US
dc.identifier.other2-s2.0-78650790484en_US
dc.identifier.urihttps://repository.li.mahidol.ac.th/handle/20.500.14594/11806
dc.rightsMahidol Universityen_US
dc.rights.holderSCOPUSen_US
dc.source.urihttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=78650790484&origin=inwarden_US
dc.subjectComputer Scienceen_US
dc.subjectMathematicsen_US
dc.titleLearning the value of a function by using hypercircle inequality for data erroren_US
dc.typeArticleen_US
dspace.entity.typePublication
mu.datasource.scopushttps://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=78650790484&origin=inwarden_US

Files

Collections