The Explanation Game.
Abstract
In 1952 Alfred Turing proposed a test which he believed might serve as a touchstone for Artificial Intelligence researchers in their efforts to model understanding by computer. The essence of this test, which Turing called the Imitation Game, was to challenge a person to distinguish between a computer program and another human being by putting questions to each via teletype. Much has been made of this test in subsequent discussions concerning the ultimate success or failure of Artificial Intelligence (AI). Unfortunately, the requirements of Turing's test are so rigorous that no program in existence today is close to succeeding, and none is likely to be for along time to come. As a result, such discussions tend toward metaphysics and away from practical scientific concerns. In this paper we examine the question of how to judge the success of an AI program from a research's point of view.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 1984
- Accession Number
- ADA140681
Entities
People
- R. C. Schank
Organizations
- Yale University