The best examples of this type are probably capable of being extended to process new classes of patterns (Grimsdale et al.,

Except for their inability to recognize patterns, machines (or, more accurately, the programs that tell machines what to do) have now met most of the classic criteria of intelligence that skeptics have proposed. They vised can outperform their designers: The checker-playing program de tion by Arthur L. Samuel of International Business Machines Corpora (1959a) usually beats him. They are original: The "Logic Theorist," a creation of a group from the Carnegie Institute of Technology and the RAND Corporation [Newell, Simon, and Shaw (1956

Man can solve problems without knowing how he solves them. We shall try to assess recent progress in understanding and mechanizing man's intellectual attainments by considering a single line of attack Chess is the intellectual game par excellence. Such characteristics mark chess as a natural arena for chine, attempts at mechanization. If one could devise a successful chess ma one would seem to have penetrated to the core of human intellectual endeavor. The history of chess programs is an example of the attempt to conceive and cope with complex mechanisms. We return to the original orientation: Humans play chess, and when they do they engage in behavior that seems extremely complex, intricate, and successful. Consider, for example, a scrap of a player's (White's) running comment as he analyzes the position in Figure 1: « Are there any other threats? Knight to Bishop 5 threatening the Queen, and also putting more pressure on the King's side because his Queen's Bishop can come over after he moves his Knight Notice that his analysis is qualitative and functional. He wanders from one feature to another, accumulating various bits of information that will be available from time to time throughout the rest of the analysis. They need not play in exactly the same way; close simulation of the human is not the immediate issue. Complexity of response is dictated by the sponse task, not by idiosyncrasies of the human re mechanism. There is a close and reciprocal relation between complexity and com On the one hand, the complexity of the systems we can specify depends on the language in which we must specify them. Being human, we have only limited capacities for processing information.

ARTIFICIAL INTELLIGENCE only remark here that problem-solving in geometry satisfies our definition of an intellectual activity, while being at the same time especially well suited to the approach we wished to explore. The fact that geometry is decidable is irrelevant for the purpose of our investigation.

Case-based reasoning is used extensively by people in A second driving force in the evolutionary history of CBR both expert and commonsense situations. It provides a was dissatisfaction with rule-based reasoning (expert systems wide range of advantages.

Although no C. Glymour, "Android Epistemology: Reflections on Artificial Intelligence general philosophical consensus has developed on most of

When working from of a small set of primitives and the statement of a such representations, lexical choice is often a nonissue program's knowledge as a set of expressions over these since each term can be uniquely associated with a natural primitives plus a set of constant terms for individuals.

Empirical rule learning and analytic Most learning is based on experience, and this requires a learning methods have predominantly used the first path, representation for the experiential input given to the whereas connectionist systems have relied on the second.

An early expression of this difficulty is the socalled might be stated that Socrates's birthplace was Athens.

J. H. Conway, On Numbers and Games, Academic Press, New In this article, a number of concepts that are of importance York, 1976. in research on game-playing programs have been J. H. Conway, "All Games Bright and Beautiful," Am.