Phép Thử Turing Test Là Gì, Phép Thử Turing (Turing Test) Là Gì

      68

What is the Turing Test?

The Turing Test is a method of inquiry in artificial intelligence (AI) for determining whether or not a computer is capable of thinking like a human being. The thử nghiệm is named after Alan Turing, the founder of the Turing Test và an English computer scientist, cryptanalyst, mathematician and theoretical biologist.

Bạn đang xem: Phép Thử Turing Test Là Gì, Phép Thử Turing (Turing Test) Là Gì

Turing proposed that a computer can be said to lớn possess artificial intelligence if it can mimic human responses under specific conditions. The original Turing Test requires three terminals, each of which is physically separated from the other two. One terminal is operated by a computer, while the other two are operated by humans.

During the demo, one of the humans functions as the questioner, while the second human & the computer function as respondents. The questioner interrogates the respondents within a specific subject area, using a specified format và context. After a preset length of time or number of questions, the questioner is then asked to decide which respondent was human & which was a computer.

The chạy thử is repeated many times. If the questioner makes the correct determination in half of the chạy thử runs or less, the computer is considered lớn have artificial intelligence because the questioner regards it as "just as human" as the human respondent.


This article is part of

A guide to lớn artificial intelligence in the enterprise

Which also includes:

History of the Turing Test

The demo is named after Alan Turing, who pioneered machine learning during the 1940s & 1950s. Turing introduced the kiểm tra in his 1950 paper called "Computing Machinery & Intelligence" while at the University of Manchester.

In his paper, Turing proposed a twist on what is called "The Imitation trò chơi." The Imitation trò chơi involves no use of AI, but rather three human participants in three separate rooms. Each room is connected via a screen & keyboard, one containing a male, the other a female, and the other containing a male or female judge. The female tries khổng lồ convince the judge that she is the male, & the judge tries to disseminate which is which.

Turing changes the concept of this game to include an AI, a human và a human questioner. The questioner"s job is then khổng lồ decide which is the AI và which is the human. Science the formation of the thử nghiệm, many AI have sầu been able khổng lồ pass; one of the first is a program created by Joseph Weizenbaum called ELIZA.

Limitations of the Turing Test

The Turing Test has been criticized over the years, in particular because historically, the nature of the questioning had lớn be limited in order for a computer to lớn exhibit human-lượt thích intelligence. For many years, a computer might only score high if the questioner formulated the queries, so they had "Yes" or "No" answers or pertained to lớn a narrow field of knowledge. When questions were open-ended and required conversational answers, it was less likely that the computer program could successfully fool the questioner.

Xem thêm: Webgoat Là Gì Về Bảo Mật? Cài Đặt Webgoat Để Học Security Testing

In addition, a program such as ELIZA could pass the Turing Test by manipulating symbols it does not understand fully. John Searle argued that this does not determine intelligence comparable to lớn humans.

To many researchers, the question of whether or not a computer can pass a Turing Test has become irrelevant. Instead of focusing on how to lớn convince someone they are conversing with a human & not a computer program, the real focus should be on how lớn make a human-machine interaction more intuitive sầu and efficient. For example, by using a conversational interface.

Variations và alternatives to lớn the Turing Test

There have sầu been a number of variations to the Turing Test to make it more relevant. Such examples include:

Total Turing Test -- where the questioner can also chạy thử perceptual abilities as well as the ability lớn manipulate objects. Minimum Intelligent Signal Test -- where only true/false và yes/no questions are given.

Alternatives to lớn Turing Tests were later developed because many see the Turing test khổng lồ be flawed. These alternatives include tests such as:

The Marcus Test -- in which a program that can "watch" a television show is tested by being asked meaningful questions about the show"s nội dung. The Lovelace Test 2.0 -- which is a kiểm tra made lớn detect AI through examining its ability to create art. Winograd Schema Challenge -- which is a chạy thử that asks multiple-choice questions in a specific format.
*
The thử nghiệm involves two humans & one machine

How is the Turing Test used today?

Although the variations of the Turing Test are often more applicable khổng lồ our current understanding of AI, the original format of the chạy thử is still used khổng lồ this day. For example, the Loebner Prize has been awarded annually since 1990 to the most human-like computer program as voted by a panel of judges. The competition follows the standard rules of the Turing Test. Critics of the award"s relevance often downplay it as more about publicity than truly testing if machines can think.

At a competition organized by the University of Reading khổng lồ mark the 60th anniversary of Turing"s death in năm trước, a chatbot called Eugene Goostman that simulates a 13-year-old boy passed the Turing Test, in the eyes of some, when it fooled 33% of the judges. This so-called first pass has been met with much criticism from those who argue that there weren"t enough judges, that other machines have performed better at the thử nghiệm in the past and that the chạy thử is invalid for only lasting five sầu minutes.

In 2018, Google Duplex successfully made an appointment with a hairdresser over the phone in front of a crowd of 7,000. The receptionist was completely unaware that they weren"t conversing with a real human. This is considered by some to lớn be a modern-day Turing Test pass, despite not relying on the true format of the kiểm tra as Alan Turing designed it.

GPT-3, a natural language processing mã sản phẩm created by OpenAI, is thought by some to have the best chance of beating the thử nghiệm in its true size of any technology that we have sầu today. But, even with its advanced text-generation abilities, many have criticized the machine because it can be tricked inkhổng lồ answering nonsensical questions & therefore would struggle under the conditions of the Turing Test.

Despite much debate about the relevance of the Turing Test today và the validity of the competitions that are based around it, the kiểm tra still stands as a philosophical starting point for discussing & researching AI. As we continue lớn make advances in AI and better understand và bản đồ how the human brain functions, the Turing Test remains foundational for defining intelligence and is a baseline for the debate about what we should expect from technologies for them to be considered thinking machines.


Related Termsartificial intelligenceArtificial intelligence is the simulation of human intelligence processes by machines, especially computer systems. Specific ... Seecompletedefinitionnarrow AI (weak AI)Narrow AI is an application of artificial intelligence technologies to enable a high-functioning system that replicates -- & ... Seecompletedefinitionnatural language generation (NLG)Natural language generation (NLG) is the use of artificial intelligence (AI) programming lớn produce written or spoken narratives ... Seecompletedefinition