Turing test
E78810
benchmark in artificial intelligence
imitation game
philosophical thought experiment
test of machine intelligence
The Turing test is a benchmark in artificial intelligence that evaluates a machine's ability to exhibit human-like intelligence by determining whether its responses are indistinguishable from those of a human in conversation.
Aliases (2)
Statements (50)
| Predicate | Object |
|---|---|
| instanceOf |
benchmark in artificial intelligence
→
imitation game → philosophical thought experiment → test of machine intelligence → |
| approach |
black-box behavioral assessment
→
|
| coreConcept |
behavioral definition of intelligence
→
imitation of human conversational behavior → |
| creator |
Alan Turing
→
|
| criticizedFor |
anthropocentric definition of intelligence
→
focus on deception rather than understanding → insufficient as a comprehensive test of intelligence → narrow focus on linguistic behavior → |
| describedIn |
Computing Machinery and Intelligence
→
|
| doesNotRequire |
inspection of internal mechanisms
→
|
| evaluationMethod |
natural language conversation
→
text-based dialogue → |
| field |
artificial intelligence
→
cognitive science → philosophy of artificial intelligence → philosophy of mind → |
| hasVariant |
Loebner Prize Turing test
→
Reverse Turing test → Total Turing test → Visual Turing test → |
| historicalSignificance |
one of the earliest formal proposals for testing machine intelligence
→
|
| inception |
1950
→
|
| influenced |
AI evaluation methodologies
→
chatbot research → development of conversational agents → |
| inspired |
Loebner Prize
→
|
| interactionMedium |
computer terminal
→
text-only communication → |
| involves |
human interlocutor
→
human judge → machine interlocutor → |
| keyCriterion |
indistinguishability from human responses
→
|
| language |
English (original formulation)
→
|
| namedAfter |
Alan Turing
→
|
| primaryGoal |
evaluate a machine's ability to exhibit human-like intelligence
→
|
| proposedQuestion |
Can machines think?
→
|
| publicationYear |
1950
→
|
| publishedIn |
Mind (journal)
→
|
| relatedConcept |
CAPTCHA
→
Chinese room argument → imitation game → machine consciousness → strong AI → weak AI → |
| successCondition |
judge cannot reliably distinguish machine from human
→
machine is misidentified as human sufficiently often → |
Referenced by (5)
| Subject (surface form when different) | Predicate |
|---|---|
|
Turing test
("Total Turing test")
→
Turing test ("Reverse Turing test") → |
hasVariant |
|
Computing Machinery and Intelligence
→
|
introducedConcept |
|
Alan Turing
→
|
knownFor |
|
Ex Machina
→
|
subject |