1
$\begingroup$

Let's us the following definition:

Tu·ring test noun

A test for intelligence in a computer, requiring that a human being should be unable to distinguish the machine from another human being by using the replies to questions put to both.

Also observe from Wikipedia:

The Turing test is a test, developed by Alan Turing in 1950, of a machine's ability to exhibit intelligent behaviour equivalent to, or indistinguishable from, that of a human.

Notice in each case a human (singular) is pitted against the demonstrated intelligence of another human (singular); WHETHER against an actual human or a machine exhibiting behaviour equivalent to or indistinguishable from the intellect of a human's int (again, singular).

In this article the question was asked whether IBM's Watson pass the Turing test. Yet Watson did not demonstrate intelligence of a single human but that of an entire team of programmers and the community of chess expertise they relied upon.

By definition Turing did not propose a test of a human against a community of humans (plural) OR against a machine exhibiting intelligent behaviour equivalent to or indistinguishable from a community of humans (plural) since whether a machine is artificially intelligent or not, a single human can nearly always be flummoxed by a community of humans given a sufficiently large community (one or more intellects). Definitions in Science are precise.

Turing's test contained the self-ordained constraint that apparent 'machine intelligence' approximated by the Turing test exhibit the approximate intelligence of a single human rather than an entire community of humans. Because of these differences the Turing Test must be distinguishable from other non-Turning Tests.

QUESTION:

If Computer Science by definition, deals with the theory and methods of processing information in digital computers including artificial intelligence, and as a matter of pragmatics, on what basis are tests between human and machine qualified or disqualified as Turing test as Turing proposed them, or some other type of test Turing didn't conceive of (say non-Turing test for artificial intelligence)?

$\endgroup$
  • 2
    $\begingroup$ The imitation game (what some people call a Turing test) was just a sample thought experiment that Turing used to explore the philosophical question of whether machines can think. He did not formally define a win in the game as a necessary and sufficient indicator of intelligence. Formally defining intelligence and designing a proper "Turing test" is still an open question that philosophers are wrestling with. I think you are taking the wrong approach here by overanalyzing vague and paraphrased definitions. $\endgroup$ – mdxn Jan 4 '17 at 3:58
  • 1
    $\begingroup$ (cont.) You might be best served by reading Turing's original paper on the matter. loebner.net/Prizef/TuringArticle.html $\endgroup$ – mdxn Jan 4 '17 at 4:02
  • $\begingroup$ Thank you. If you believe that paper answers the question, might I ask why you didn't provide a response citing the paper? Whats the harm, if not risk having people agree or disagree with your answer? Can you explain why Turing's original paper addresses the question, except provide an answer rather than a comment. With respect to the test being a 'thought experiment', Einstein's General Theory of Relativity started a thought experiment. Is it not prudent to ask what Turning meant? $\endgroup$ – user34445 Jan 4 '17 at 4:30
  • $\begingroup$ 1. Please ask only one question per question. This site's format doesn't work so well when you try to ask more than one question in a single post. Instead, please ask each question separately, in its own post. It might be helpful to edit this post to focus on just one of the questions, and post the other one separately. 2. I don't know how well you know our format, but our site is aimed at questions that admit an objectively correct answer. If your goal is to have a discussion about the topic, then you shouldn't be asking here. See our help center. $\endgroup$ – D.W. Jan 4 '17 at 4:33
  • $\begingroup$ No the goal was to obtain an answer. Ill remove one of the questions .. $\endgroup$ – user34445 Jan 4 '17 at 5:31

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.