Please use this identifier to cite or link to this item:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorXu, Zhaoen
dc.contributor.authorSong, Qingen
dc.contributor.authorHaijin, Fanen
dc.contributor.authorWang, Danweien
dc.identifier.citationXu, Z., Song, Q., Haijin, F., & Wang, D. (2012). Online prediction of time series data with recurrent kernels. The 2012 International Joint Conference on Neural Networks (IJCNN).en
dc.description.abstractWe propose a robust recurrent kernel online learning (RRKOL) algorithm which allows the exploitation of the kernel trick in an online fashion. The novel RRKOL algorithm achieves guaranteed weight convergence with regularized risk management through the recurrent hyper-parameters for a superior generalization performance. To select useful data to be learned and remove redundant ones, a sparcification procedure is developed based on the stability analysis of the system. Two time-series prediction examples are presented.en
dc.rights© 2012 IEEE.en
dc.subjectDRNTU::Engineering::Electrical and electronic engineeringen
dc.titleOnline prediction of time series data with recurrent kernelsen
dc.typeConference Paperen
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen
dc.contributor.conferenceInternational Joint Conference on Neural Networks (2012 : Brisbane, Australia)en
item.fulltextNo Fulltext-
Appears in Collections:EEE Conference Papers

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.