Turing test

(redirected from Turing tests)
Also found in: Dictionary, Encyclopedia.

Turing test

A test of artificial intelligence devised by UK mathematician, Alan Turing, who predicted in 1950 that by 2000, a computer could be programmed so that after 5 minutes of questioning, the average interrogator would not have more than a 70% chance of telling whether he or she was talking to a machine or a human. The state of AI has advanced to the degree that for the 2010 Loebner Prize—a platform for Turing Tests—the interaction time was increased to 25 minutes.
Mentioned in ?
References in periodicals archive ?
While judges' correct responses varied across characters, for each visual Turing test, fewer than 25 percent of judges performed significantly better than chance in assessing whether a machine or a human produced a given set of symbols.
The CAPTCHA relay attack is also called Automated Turing Test relay attack in (Van & Stubblebine, 2006) and "stealing cycles from humans" (Kopsell & Hilling, 2004).
Verification of a human in the loop, or identification via the Turing test.http://www.wisdom.weizmann.ac.il/ naor/PAPERS/human.ps, 2008.
Given the attraction of electronic delivery, you'd think somebody would be offering an e-reader that provides an experience that is nearly indistinguishable from print, with the economies of electronic delivery, a kind of Turing test for e-readers: reliable replacement for print products; color display; compatibility with the de facto electronic document format, Adobe PDF; printing (to paper or PDF) for offline viewing, while costing less than paper.
In the Turing Test, the objective was/is to determine, through a process of questioning and answers, the nature/character of an "other," be this nature/ character gender or ontological status--person or computer.
The game has since become known as the "Turing Test," a term that has eclipsed even his eponymous machine in Turning's terminological legacy.
But to the extent that it is, it can be criticized on the same grounds as other topic-and time-limited Turing tests (Shieber 2014b).
(1) To avoid the need to define intelligence or thinking, terms that he uses interchangeably, Turing asks whether there are "imaginable digital computers which would do well" in a game he defines and calls "the imitation game," and which we know as the Turing test. The Turing test poses the challenge of constructing a computer system able to carry on a dialogue with a person, potentially ranging over any subject matter and many subject matters, well enough to be indistinguishable from a person.
For this reason we propose a stronger version of the original Turing test. In particular, we describe here an open-ended set of Turing++ questions that we are developing at the Center for Brains, Minds, and Machines at MIT--that is questions about an image.
That paper is the basis of the so-called Turing Test for the ability of a machine to demonstrate intelligence.
Bad software gives Lanier a novel spin on the "Turing Test," which attempts to gauge whether machine intelligence has evolved to the point that it is indistinguishable from human intelligence.