%0 Journal Article
%T 先验知识与基于核函数的回归方法的融合
%A 孙喆
%A 张曾科
%A 王焕钢
%J 自动化学报
%P 1515-1521
%D 2008
%R 10.3724/SP.J.1004.2008.01515
%X ？Insomesamplebasedregressiontasks,theobservedsamplesarequitefewornotinformativeenough.Asaresult,theconflictbetweenthenumberofsamplesandthemodelcomplexityemerges,andtheregressionmethodwillconfrontthedilemmawhethertochooseacomplexmodelornot.Incorporatingthepriorknowledgeisapotentialsolutionforthisdilemma.Inthispaper,asortofthepriorknowledgeisinvestigatedandanovelmethodtoincorporateitintothekernelbasedregressionschemeisproposed.Theproposedpriorknowledgebasedkernelregression(PKBKR)methodincludestwosubproblems:representingthepriorknowledgeinthefunctionspace,andcombiningthisrepresentationandthetrainingsamplestoobtaintheregressionfunction.Agreedyalgorithmfortherepresentingstepandaweightedlossfunctionfortheincorporationstepareproposed.Finally,experimentsareperformedtovalidatetheproposedPKBKRmethod,whereintheresultsshowthattheproposedmethodcanachieverelativelyhighregressionperformancewithappropriatemodelcomplexity,especiallywhenthenumberofsamplesissmallortheobservationnoiseislarge.
%K Machinelearning
%K priorknowledge
%K kernelbasedregression
%K iterativegreedyalgorithm
%K weightedlossfunction
%U http://www.aas.net.cn/CN/abstract/abstract18030.shtml