| dbo:abstract |
The Alignment Problem: Machine Learning and Human Values is a 2020 non-fiction book by the American writer Brian Christian. It is based on numerous interviews with experts trying to build artificial intelligence systems, particular machine learning systems, that are aligned with human values. (en) |
| dbo:author |
dbr:Brian_Christian |
| dbo:isbn |
0393635821 |
| dbo:nonFictionSubject |
dbr:AI_alignment |
| dbo:numberOfPages |
496 (xsd:positiveInteger) |
| dbo:oclc |
1137850003 |
| dbo:publisher |
dbr:W._W._Norton_&_Company |
| dbo:releaseDate |
2020-10-06 (xsd:date) |
| dbo:thumbnail |
wiki-commons:Special:FilePath/The_Alignment_Problem_book_cover.jpg?width=300 |
| dbo:wikiPageExternalLink |
https://brianchristian.org/the-alignment-problem/ |
| dbo:wikiPageID |
69438830 (xsd:integer) |
| dbo:wikiPageLength |
7440 (xsd:nonNegativeInteger) |
| dbo:wikiPageRevisionID |
1106488873 (xsd:integer) |
| dbo:wikiPageWikiLink |
dbr:Behaviorism dbr:ProPublica dbr:Publishers_Weekly dbr:Satya_Nadella dbc:Futurology_books dbr:Brian_Christian dbr:DeepMind dbr:Julia_Angwin dbr:Perceptron dbc:English-language_books dbc:English_non-fiction_books dbc:W._W._Norton_&_Company_books dbr:Nature_(journal) dbr:The_New_York_Times dbr:The_Wall_Street_Journal dbr:Machine_learning dbr:Artificial_neural_networks dbr:Actualism dbr:Toby_Ord dbr:W._W._Norton_&_Company dbr:William_MacAskill dbc:Books_about_effective_altruism dbc:Books_about_existential_risk dbr:AI_alignment dbr:AlphaGo dbr:AlphaZero dbr:Ezra_Klein dbr:Fast_Company dbr:Normative dbr:Global_catastrophic_risk dbr:Reinforcement_learning dbr:Artificial_intelligence dbc:2020_non-fiction_books dbc:Existential_risk_from_artificial_general_intelligence dbr:AlexNet dbr:Kate_Crawford dbr:Black_box dbr:Effective_altruism dbr:Dopamine dbr:COMPAS_(software) dbr:Possibilism_(philosophy) dbr:Human_Compatible dbr:Psychological dbr:Kirkus_Reviews dbr:Recidivism dbr:Inverse_reinforcement_learning dbr:Superintelligence:_Paths,_Dangers,_Strategies dbr:Existential_risk |
| dbp:author |
dbr:Brian_Christian |
| dbp:caption |
Hardcover edition (en) |
| dbp:country |
United States (en) |
| dbp:isbn |
393635821 (xsd:integer) |
| dbp:language |
English (en) |
| dbp:mediaType |
Print, e-book, audiobook (en) |
| dbp:name |
The Alignment Problem: Machine Learning and Human Values (en) |
| dbp:oclc |
1137850003 (xsd:integer) |
| dbp:pages |
496 (xsd:integer) |
| dbp:publisher |
dbr:W._W._Norton_&_Company |
| dbp:releaseDate |
2020-10-06 (xsd:date) |
| dbp:subject |
dbr:AI_alignment |
| dbp:website |
https://brianchristian.org/the-alignment-problem/ |
| dbp:wikiPageUsesTemplate |
dbt:Effective_altruism dbt:About dbt:Infobox_book dbt:Reflist dbt:Short_description dbt:Use_dmy_dates |
| dc:publisher |
W. W. Norton & Company |
| dct:subject |
dbc:Futurology_books dbc:English-language_books dbc:English_non-fiction_books dbc:W._W._Norton_&_Company_books dbc:Books_about_effective_altruism dbc:Books_about_existential_risk dbc:2020_non-fiction_books dbc:Existential_risk_from_artificial_general_intelligence |
| rdf:type |
owl:Thing bibo:Book schema:Book schema:CreativeWork dbo:Work wikidata:Q234460 wikidata:Q386724 wikidata:Q571 dbo:Book dbo:WrittenWork |
| rdfs:comment |
The Alignment Problem: Machine Learning and Human Values is a 2020 non-fiction book by the American writer Brian Christian. It is based on numerous interviews with experts trying to build artificial intelligence systems, particular machine learning systems, that are aligned with human values. (en) |
| rdfs:label |
The Alignment Problem (en) |
| owl:sameAs |
wikidata:The Alignment Problem https://global.dbpedia.org/id/GK4LM |
| prov:wasDerivedFrom |
wikipedia-en:The_Alignment_Problem?oldid=1106488873&ns=0 |
| foaf:depiction |
wiki-commons:Special:FilePath/The_Alignment_Problem_book_cover.jpg |
| foaf:homepage |
https://brianchristian.org/the-alignment-problem/ |
| foaf:isPrimaryTopicOf |
wikipedia-en:The_Alignment_Problem |
| foaf:name |
The Alignment Problem: Machine Learning and Human Values (en) |
| is dbo:notableWork of |
dbr:Brian_Christian |
| is dbo:wikiPageRedirects of |
dbr:Machine_Learning_and_Human_Values |
| is dbo:wikiPageWikiLink of |
dbr:Brian_Christian dbr:Existential_risk_from_artificial_general_intelligence dbr:Atlas_of_AI dbr:Machine_Learning_and_Human_Values |
| is foaf:primaryTopic of |
wikipedia-en:The_Alignment_Problem |
