Turing test
<artificial intelligence> A criterion proposed by
Alan Turing in 1950 for deciding whether a computer is intelligent.
Turing called it "the Imitation Game" and offered it as a replacement for the question, "Can machines think?"
A human holds a written conversation on any topic with an unseen correspondent (nowadays it might be by
electronic mail or
chat).
If the human believes he is talking to another human when he is really talking to a computer then the computer has passed the Turing test and is deemed to be intelligent.
Turing predicted that within 50 years (by the year 2000) technological progress would produce computing machines with a capacity of 10**9 bits, and that with such machinery, a computer program would be able to fool the average questioner for 5 minutes about 70% of the time.
The
Loebner Prize is a competition to find a computer program which can pass an unrestricted Turing test.
Julia (http://fuzine.mt.cs.cmu.edu/mlm/julia.html) is a program that attempts to pass the Turing test.
See also
AI-complete.
Turing's paper (http://cogprints.ecs.soton.ac.uk/archive/00000499/00/turing.html).
