Treść książki
Przejdź do opcji czytnikaPrzejdź do nawigacjiPrzejdź do informacjiPrzejdź do stopki
Wstęp:wprowadzeniedobezpieczeństwaiochronysztucznejinteligencji
xxv
40.R.V
.YampolskiyandJ.Fox,“Safetyengineeringforartificialgeneralintelligence,”Topoi.Special
IssueonMachineEthics&theEthicsofBuildingIntelligentMachines,2012.
41.L.MuehlhauserandR.Yampolskiy,“RomanYampolskiyonAISafetyEngineering,”presented
attheMachineIntelligenceResearchInstitute,July15,2013,Availableat:http://intelligence.
org/2013/07/15/roman-interview/.
42.R.V.Yampolskiy,“Artificialintelligencesafetyengineering:Whymachineethicsisawrong
approach,”inPhilosophyandTheoryofArtificialIntelligence,SpringerBerlinHeidelberg,2013,
pp.389-396.
43.A.M.MajotandR.V
.Yampolskiy,“AISafetyEngineeringthroughIntroductionofSelf-Reference
intoFelicificCalculusviaArtificialPainandPleasure,”inIEEEInternationalSymposiumonEthics
inScience,TechnologyandEngineering,Chicago,IL,May23-24,2014,pp.1-6.
44.R.V
.Yampolskiy,“ArtificialSuperintelligence:aFuturisticApproach,”ChapmanandHall/CRC,
2015.
45.R.V
.Yampolskiy,“Whataretheultimatelimitstocomputationaltechniques:verifiertheoryand
unverifiability,”PhysicaScripta,vol.92,p.093001,2017.
46.A.RamamoorthyandR.Yampolskiy,“Beyondmad?:Theraceforartificialgeneralintelligence,”
ITUJournal:ICTDiscoveries,2017.
47.M.Brundage,S.Avin,J.Clark,H.Toner,P.Eckersley,B.Garfinkeletal.,“TheMaliciousUseof
ArtificialIntelligence:Forecasting,Prevention,andMitigation,”arXivpreprintarXiv:1802.07228,
2018.
48.J.H.Moor,“Thenature,importance,anddifficultyofmachineethics,”IEEEIntelligentSystems,
vol.21,pp.18-21,2006.
49.E.Yudkowsky,“CreatingfriendlyAI1.0:Theanalysisanddesignofbenevolentgoalarchitectures,”
inSingularityInstituteforArtificialIntelligence,SanFrancisco,CA,June,vol.15,2001.
50.R.Yampolskiy,“Leakproofingthesingularityartificialintelligenceconfinementproblem,”Journal
ofConsciousnessStudies,vol.19,pp.1-2,2012.
51.J.Babcock,J.Kramar,andR.Yampolskiy,“TheAGIContainmentProblem,”arXivpreprint
arXiv:1604.00545,2016.
52.J.Babcock,J.Kramar,andR.Yampolskiy,“TheAGIContainmentProblem,”inTheNinth
ConferenceonArtificialGeneralIntelligence(AGI2015),2016.
53.S.ArmstrongandR.V
.Yampolskiy,“SecuritySolutionsforIntelligentandComplexSystems,”in
SecuritySolutionsforHyperconnectivityandtheInternetofThings,IGIGlobal,2016,pp.37-88.
54.R.M.Karp,“ReducibilityAmongCombinatorialProblems,”inComplexityofComputer
Computations,R.E.MillerandJ.W.Thatcher,Eds.,NewYork:Plenum,1972,pp.85-103.
55.R.Yampolskiy,“TuringTestasaDefiningFeatureofAI-Completeness,”inArtificialIntelligence,
EvolutionaryComputingandMetaheuristics.vol.427,X.-S.Yang,Ed.,BerlinHeidelberg:Springer,
2013,pp.3-17.
56.R.V
.Yampolskiy,“AI-Complete,AI-Hard,orAI-Easy-ClassificationofProblemsinAI,”inThe
23rdMidwestArtificialIntelligenceandCognitiveScienceConference,Cincinnati,OH,USA,2012.
57.R.V.Yampolskiy,“Efficiencytheory:Aunifyingtheoryforinformation,computationand
intelligence,”JournalofDiscreteMathematicalSciences&Cryptography,vol.16(45),pp.259-
277,2013.
58.R.V
.Yampolskiy,“AI-CompleteCAPTCHAsaszeroknowledgeproofsofaccesstoanartificially
intelligentsystem,”ISRNArtificialIntelligence,vol.271878,2011.
59.R.V.Yampolskiy,“OntheOriginofSamples:AttributionofOutputtoaParticularAlgorithm,”
arXivpreprintarXiv:1608.06172,2016.
60.K.Sotala,“DefiningHumanValuesforValueLearners,”in2ndInternationalWorkshoponAI,
EthicsandSociety,AAAI-2016,2016.
61.D.Dewey,“Learningwhattovalue,”ArtificialGeneralIntelligence,pp.309-314,2011.
62.N.SoaresandB.Fallenstein,“Aligningsuperintelligencewithhumaninterests:Atechnicalresearch
agenda,”MachineIntelligenceResearchInstitute(MIRI)TechnicalReport,vol.8,2014.
