Introduction to Statistical Learning Theory
Introductionto StatisticalLearningTheoryOlivierBousquet 1, St ephaneBoucheron2, andG aborLugosi31Max-Planck ,D-72076T e deParis-Sud,Laboratoired'InformatiqueB^a timent 490,F-91405Orsay tostudy, ina sta-tisticalframework, ,mostresultstake statisticallearningtheoryis toprovidea frameworkforstudy-ingtheproblemofinferen ce,thatis ofgainingknowledge,makingpredictions,mak ingdecisionsorconstructingmodelsfroma studiedinastatisticalframework,thatis thereareassumptionsofstatisticalnatureab outtheunderlyingphenomena(intheway thedatais generated).Asa motivationfortheneedofsuch a Theory , :(Vapnik,[1]) Nothingis morepracticalthana good ,a theoryofinferenceshouldbe abletogive a formalde nitionofwordslike Learning ,generalization,over tting,andalsotocharacterizetheperformanc eoflearningalgorithmssothat,ultimately, itmay goals:make thingsmorepreciseandderive understudyhereis theprocessof inductive inferencewhich canroughlybe summarizedasthefollowingsteps:176Bousque t,Boucheron& a predictionsusingthismodelOfcourse,thisde nitionis verygeneralandcouldbe toactuallyautomatethisprocessandthego
3. Make predictions using this model Of course, this de nition is very general and could be taken more or less as the goal of Natural Sciences. The goal of Machine Learning is to actually automate this process and the goal of Learning Theory is to formalize it. In this tutorial we consider a special case of the above process which is the
Download Introduction to Statistical Learning Theory
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: