资源预览内容
第1页 / 共16页
第2页 / 共16页
第3页 / 共16页
第4页 / 共16页
第5页 / 共16页
第6页 / 共16页
第7页 / 共16页
第8页 / 共16页
第9页 / 共16页
第10页 / 共16页
亲,该文档总共16页,到这儿已超出免费预览范围,如果喜欢就下载吧!
资源描述
InductiveandAnalyticalLearningInductivelearningAnalyticallearningHypothesis?tsdataHypothesis?tsdomaintheoStatisticalinferenceDeductiveinferenceRequireslittlepriorknowledgeLearnsfromscarcedataSyntacticinductivebiasBiasisdomaintheory?WhatWeWouldLikeAnalytical learningInductive learningPlentiful data No prior knowledgePerfect prior knowledgeScarce dataGeneralpurposelearningmethod?Nodomaintheory?learnaswellasinductivemethods?Perfectdomaintheory?learnaswellasProlog?EBG?Accomodatearbitraryandunknownerrorsindomaintheory?Accomodatearbitraryandunknownerrorsintrainingdata?Domaintheory?Cup?Stable?Liftable?OpenVesselStable?BottomIsFlatLiftable?Graspable?LightGraspable?HasHandleOpenVessel?HasConcavity?ConcavityPointsUpTrainingexamples?CupsNon?CupsBottomIsFlatppppppppConcavityPointsUppppppppExpensiveppppFragileppppppHandleOnTopppHandleOnSidepppHasConcavitypppppppppHasHandlepppppLightppppppppMadeOfCeramicppppMadeOfPaperppMadeOfStyrofoampppp?KBANNKBANN?dataD?domaintheoryB?CreateafeedforwardnetworkhequivalenttoB?UseBackproptotunehto?tD?NeuralNetEquivalenttoDomainTheoryHasHandle HandleOnTop HandleOnSideBottomIsFlatHasConcavity ConcavityPointsUpLightMadeOfCeramicMadeOfPaperMadeOfStyrofoamExpensiveFragileCupStableLiftableOpenVesselGraspable?CreatingNetworkEquivalenttoDo?mainTheoryCreateoneunitperhornclauserule?i?e?anANDunit?Connectunitinputstocorrespondingclauseantecedents?Foreachnon?negatedantecedent?correspondinginputweightw?W?whereWissomeconstant?Foreachnegatedantecedent?inputweightw?W?Thresholdweightw?n?W?wherenisnumberofnon?negatedantecedentsFinally?addmanyadditionalconnectionswithnear?zeroweightsLiftable?Graspable?Heavy?Resultofre?ningthenetworkHasHandle HandleOnTop HandleOnSideBottomIsFlatHasConcavity ConcavityPointsUpLightMadeOfCeramicMadeOfPaperMadeOfStyrofoamExpensiveFragileStableLiftableOpen-VesselLarge positive weight Large negative weight Negligible weightCupGraspable?KBANNResultsClassifyingpromoterregionsinDNAleaveoneouttesting?Backpropagation?errorrate?KBANN?Similarimprovementsonotherclassi?cation?controltasks?HypothesisspacesearchinKBANNHypothesis SpaceHypotheses that fit training data equally well Initial hypothesis for KBANNInitial hypothesis for BACKPROPAGATION?EBNNKeyidea?Previouslylearnedapproximatedomaintheory?Domaintheoryrepresentedbycollectionofneuralnetworks?Learntargetfunctionasanotherneuralnetwork?BottomIsFlat ConcavityPointsUp Expensive Fragile HandleOnTop HandleOnSide HasConcavity HasHandle Light MadeOfCeramic MadeOfPaper MadeOfStyrofoamCupBottomIsFlat ConcavityPointsUp Expensive Fragile HandleOnTop HandleOnSide HasConcavity HasHandle Light MadeOfCeramic MadeOfPaper MadeOfStyrofoam= T = T = T = T = F = T = T = T = T = T = F = FGraspableStableOpenVesselLiftableCupTarget network:0.20.8Training derivativesCuptargetExplanation of training example in terms of domain theory:Cup = T?Modi?edObjectiveforGradientDescentE?Xi?f?xi?f?xi?iXj?BBB?A?x?xj?f?x?xj?CCCA?x?xi?where?i?jA?xi?f?xi?jc?f?x?istargetfunction?f?x?isneuralnetapproximationtof?x?A?x?isdomaintheoryapproximationtof?x?xxfxxx123f(x)gh f(x )1 f(x )2 f(x )3x?HypothesisSpaceSearchinEBNNHypotheses that maximize fit to dataHypothesis SpaceBACKPROPAGATION SearchTANGENTPROP SearchHypotheses that maximize fit to data and prior knowledge?SearchinFOCL.2+,32+,32+,44+,2Generated by thedomain theoryCupHasHandleCupHasHandleCupFragileCupBottomIsFlat, Light, HasConcavity, ConcavityPointsUpCup2+,00+,24+,0.CupBottomIsFlat, Light, HasConcavity, ConcavityPointsUp HandleOnTopBottomIsFlat, Light, HasConcavity, ConcavityPointsUp,HandleOnTopBottomIsFlat, Light, HasConcavity, ConcavityPointsUp, HandleOnSideCupCup?FOCLResultsRecognizinglegalchessendgamepositions?positive?negativeexamples?FOIL?FOCL?usingdomaintheorywith?accuracy?NYNEXtelephonenetworkdiagnosis?trainingexamples?FOIL?FOCL?usingdomaintheorywith?accuracy?
收藏 下载该资源
网站客服QQ:2055934822
金锄头文库版权所有
经营许可证:蜀ICP备13022795号 | 川公网安备 51140202000112号