Treść książki
Przejdź do opcji czytnikaPrzejdź do nawigacjiPrzejdź do informacjiPrzejdź do stopki
xxiv
Wstęp:wprowadzeniedobezpieczeństwaiochronysztucznejinteligencji
15.C.Hewitt,“DevelopmentofLogicProgramming:Whatwentwrong,whatwasdoneaboutit,and
whatitmightmeanforthefuture,”inWhatWentWrongandWhy:LessonsfromAIResearchand
Applications:Papersfromthe2008AAAIWorkshop.MenloPark,California:AAAIPress,2008.
16.J.R.Meehan,“TALE-SPIN,AnInteractiveProgramthatWritesStories,”inIJCAI,1977,pp.91-98.
17.B.FriedmanandH.Nissenbaum,“Biasincomputersystems,”ACMTransactionsonInformation
Systems(TOIS),vol.14,pp.330-347,1996.
18.S.LowryandG.Macpherson,“Ablotontheprofession,”BritishMedicalJournal(Clinical
ResearchEd.),vol.296,p.657,1988.
19.K.Sims,“EvolvingVirtualCreatures,”inProceedingsofthe21stAnnualConferenceonComputer
GraphicsandInteractiveTechniques,1994,pp.15-22.
20.M.Tambe,“Electricelves:Whatwentwrongandwhy,”AIMagazine,vol.29,p.23,2008.
21.A.Liu,C.E.Martin,T.Hetherington,andS.Matzner,“AILessonsLearnedfromExperimentsin
InsiderThreatDetection,”inAAAISpringSymposium:WhatWentWrongandWhy:Lessonsfrom
AIResearchandApplications,2006,pp.49-55.
22.J.GundersonandL.Gunderson,“AndThenthePhoneRang,”inAAAISpringSymposium:What
WentWrongandWhy:LessonsfromAIResearchandApplications,2006,pp.13-18.
23.C.Szegedy,W.Zaremba,I.Sutskever,J.Bruna,D.Erhan,I.Goodfellowetal.,“Intriguingproperties
ofneuralnetworks,”arXivpreprintarXiv:1312.6199,2013.
24.L.Sweeney,“Discriminationinonlineaddelivery,”Queue,vol.11,p.10,2013.
25.N.Diakopoulos,“Algorithmicdefamation:Thecaseoftheshamelessautocomplete,”TowCenter
forDigitalJournalism,2014.
26.R.Caruana,Y.Lou,J.Gehrke,P.Koch,M.Sturm,andN.Elhadad,“IntelligibleModelsfor
Healthcare:PredictingPneumoniaRiskandHospital30-dayReadmission,”inProceedingsofthe
21thACMSIGKDDInternationalConferenceonKnowledgeDiscoveryandDataMining,2015,
pp.1721-1730.
27.M.T.Ribeiro,S.Singh,andC.Guestrin,“WhyShouldITrustYou?:ExplainingthePredictionsof
AnyClassifier,”inProceedingsofthe22ndACMSIGKDDInternationalConferenceonKnowledge
DiscoveryandDataMining,2016,pp.1135-1144.
28.A.Caliskan,J.J.Bryson,andA.Narayanan,“Semanticsderivedautomaticallyfromlanguage
corporacontainhuman-likebiases,”Science,vol.356,pp.183-186,2017.
29.S.Armstrong,A.Sandberg,andN.Bostrom,“Thinkinginsidethebox:Controllingandusingan
oracleai,”MindsandMachines,vol.22,pp.299-324,2012.
30.N.Bostrom,“Ethicalissuesinadvancedartificialintelligence,”ScienceFictionandPhilosophy:
FromTimeTraveltoSuperintelligence,pp.277-284,2003.
31.J.Taylor,E.Yudkowsky,P.LaVictoire,andA.Critch,“Alignmentforadvancedmachinelearning
systems,”MachineIntelligenceResearchInstitute,2016.
32.E.Yudkowsky,“ComplexvaluesystemsinfriendlyAI,”ArtificialGeneralIntelligence,pp.388-
393,2011.
33.G.Marcus,“Moralmachines,”TheNewYorker,vol.24,2012.
34.D.E.DenningandP.J.Denning,“Artificialstupidity,”AssociationforComputingMachinery.
CommunicationsoftheACM,vol.47,no.5,p.112,2004.
35.M.Chessen,“TheMADCOMFuture,”AtlanticCouncil,Availableat:http://www.atlanticcouncil.
org/publications/reports/the-madcom-future,2017.
36.A.Krishnan,KillerRobots:LegalityandEthicalityofAutonomousWeapons.AshgatePublishing,
Ltd.,2009.
37.L.Gloor,“Suffering-focusedAIsafety:Why“fail-safe”measuresmightbeourtopintervention,”
TechnicalReportFRI-16-1.FoundationalResearchInstitute.https://foundationalresearch.org/
wp-content/uploads/2016/08/Suffering-focused-AI-safety.pdf2016.
38.D.Amodei,C.Olah,J.Steinhardt,P.Christiano,J.Schulman,andD.Mané,“Concreteproblemsin
AIsafety,”arXivpreprintarXiv:1606.06565,2016.
39.R.V.Yampolskiy,“ArtificialIntelligenceSafetyEngineering:WhyMachineEthicsisaWrong
Approach,”presentedatthePhilosophyandTheoryofArtificialIntelligence(PT-AI2011),
Thessaloniki,Greece,October3-4,2011.
