您好,欢迎访问三七文档
当前位置:首页 > IT计算机/网络 > AI人工智能 > Negnevitsky人工智能英文讲义一52
Negnevitsky,PearsonEducation,20021Lecture1Introductiontoknowledge-baseintelligentsystemsIntelligentmachines,orwhatmachinescandoThehistoryofartificialintelligenceorfromthe“DarkAges”toknowledge-basedsystemsSummaryNegnevitsky,PearsonEducation,20022Intelligentmachines,orwhatmachinescandoPhilosophershavebeentryingforover2000yearstounderstandandresolvetwoBigQuestionsoftheUniverse:Howdoesahumanmindwork,andCannon-humanshaveminds?Thesequestionsarestillunanswered.Intelligenceistheabilitytounderstandandlearnthings.2Intelligenceistheabilitytothinkandunderstandinsteadofdoingthingsbyinstinctorautomatically.(EssentialEnglishDictionary,Collins,London,1990)Negnevitsky,PearsonEducation,20023Inordertothink,someoneorsomethinghastohaveabrain,oranorganthatenablessomeoneorsomethingtolearnandunderstandthings,tosolveproblemsandtomakedecisions.Sowecandefineintelligenceastheabilitytolearnandunderstand,tosolveproblemsandtomakedecisions.Thegoalofartificialintelligence(AI)asascienceistomakemachinesdothingsthatwouldrequireintelligenceifdonebyhumans.Therefore,theanswertothequestionCanMachinesThink?wasvitallyimportanttothediscipline.Theanswerisnotasimple“Yes”or“No”.Negnevitsky,PearsonEducation,20024Somepeoplearesmarterinsomewaysthanothers.Sometimeswemakeveryintelligentdecisionsbutsometimeswealsomakeverysillymistakes.Someofusdealwithcomplexmathematicalandengineeringproblemsbutaremoronicinphilosophyandhistory.Somepeoplearegoodatmakingmoney,whileothersarebetteratspendingit.Ashumans,weallhavetheabilitytolearnandunderstand,tosolveproblemsandtomakedecisions;however,ourabilitiesarenotequalandlieindifferentareas.Therefore,weshouldexpectthatifmachinescanthink,someofthemmightbesmarterthanothersinsomeways.Negnevitsky,PearsonEducation,20025Oneofthemostsignificantpapersonmachineintelligence,“ComputingMachineryandIntelligence”,waswrittenbytheBritishmathematicianAlanTuringoverfiftyyearsago.However,itstillstandsupwellunderthetestoftime,andtheTuring’sapproachremainsuniversal.Heasked:Istherethoughtwithoutexperience?Istheremindwithoutcommunication?Istherelanguagewithoutliving?Isthereintelligencewithoutlife?Allthesequestions,asyoucansee,arejustvariationsonthefundamentalquestionofartificialintelligence,Canmachinesthink?Negnevitsky,PearsonEducation,20026Turingdidnotprovidedefinitionsofmachinesandthinking,hejustavoidedsemanticargumentsbyinventingagame,theTuringImitationGame.Theimitationgameoriginallyincludedtwophases.Inthefirstphase,theinterrogator,amanandawomanareeachplacedinseparaterooms.Theinterrogator’sobjectiveistoworkoutwhoisthemanandwhoisthewomanbyquestioningthem.Themanshouldattempttodeceivetheinterrogatorthatheisthewoman,whilethewomanhastoconvincetheinterrogatorthatsheisthewoman.Negnevitsky,PearsonEducation,20027TuringImitationGame:Phase1Negnevitsky,PearsonEducation,20028TuringImitationGame:Phase2Inthesecondphaseofthegame,themanisreplacedbyacomputerprogrammedtodeceivetheinterrogatorasthemandid.Itwouldevenbeprogrammedtomakemistakesandprovidefuzzyanswersinthewayahumanwould.Ifthecomputercanfooltheinterrogatorasoftenasthemandid,wemaysaythiscomputerhaspassedtheintelligentbehaviourtest.Negnevitsky,PearsonEducation,20029TuringImitationGame:Phase2Negnevitsky,PearsonEducation,200210TheTuringtesthastworemarkablequalitiesthatmakeitreallyuniversal.Bymaintainingcommunicationbetweenthehumanandthemachineviaterminals,thetestgivesusanobjectivestandardviewonintelligence.Thetestitselfisquiteindependentfromthedetailsoftheexperiment.Itcanbeconductedasatwo-phasegame,orevenasasingle-phasegamewhentheinterrogatorneedstochoosebetweenthehumanandthemachinefromthebeginningofthetest.Negnevitsky,PearsonEducation,200211Turingbelievedthatbytheendofthe20thcenturyitwouldbepossibletoprogramadigitalcomputertoplaytheimitationgame.AlthoughmoderncomputersstillcannotpasstheTuringtest,itprovidesabasisfortheverificationandvalidationofknowledge-basedsystems.Aprogramthoughtintelligentinsomenarrowareaofexpertiseisevaluatedbycomparingitsperformancewiththeperformanceofahumanexpert.Tobuildanintelligentcomputersystem,wehavetocapture,organiseandusehumanexpertknowledgeinsomenarrowareaofexpertise.Negnevitsky,PearsonEducation,200212ThehistoryofartificialintelligenceThefirstworkrecognisedinthefieldofAIwaspresentedbyWarrenMcCullochandWalterPittsin1943.Theyproposedamodelofanartificialneuralnetworkanddemonstratedthatsimplenetworkstructurescouldlearn.McCulloch,thesecond“foundingfather”ofAIafterAlanTuring,hadcreatedthecornerstoneofneuralcomputingandartificialneuralnetworks(ANN).Thebirthofartificialintelligence(1943–1956)Negnevitsky,PearsonEducation,200213ThethirdfounderofAIwasJohnvonNeumann,thebrilliantHungarian-bornmathematician.In1930,hejoinedthePrincetonUniversity,lecturinginmathematicalphysics.HewasanadviserfortheElectronicNumericalIntegratorandCalculatorprojectattheUniversityofPennsylvaniaandhelpedtodesigntheElectronicDiscreteVariableCalculator.HewasinfluencedbyMcCullochandPitts’sneuralnetworkmodel.WhenMarvinMinskyandDeanEdmonds,twograduatestudentsinthePrincetonmathematicsd
本文标题:Negnevitsky人工智能英文讲义一52
链接地址:https://www.777doc.com/doc-25858 .html