Results


HEARSAY-II / 349

Classics (Collection 2)

Carnegie-Mellon University, Pittsburgh, Pennsylvania 15213 The Hearsay-H system, developed during the DARPAsponsored five-year speechunderstanding research program, represents both a specific solution to the speechunderstanding problem and a general framework for coordinating independent processes to achieve cooperative problem-solving behavior. As a computational problem, speech understanding reflects a large number of intrinsically interesting issues. Spoken sounds are achieved by a long chain of successive transformations, from intentions, through semantic and syntactic structuring, to the eventually resulting audible acoustic waves. As a consequence, interpreting speech means effectively inverting these transformations to recover the speaker's intention from the sound. At each step in the interpretive process, ambiguity and uncertainty arise.


Proceedings

Classics (Collection 2)

VICTORIA, B. C. 14, 15, 16 MAY 1980 3. Goal Subsumption - Goal subsumption gives rise to dramatic situations when a subsumption state is terminated. For example, if John is happily married to Mary, and then Mary leaves him, all the goals subsumed by their relationship may now be problematic - John may become lonely, and miss his social interactions with Mary, for instance. Closely related to problems based on goal subsumption are those caused by the elimination of normal physical states. For example, becoming very depressed or losing a bodily function can give rise to the inability to fulfill recurring goals, and can therefore generate some interesting problems. The resolution of goal subsumption termination involves establishing a new subsumption state to re-subsume the recurring goals.


21 Knowledge Representation

Classics (Collection 2)

Archaeology is thus one of the social sciences. But compared with'mainstream' social sciences such as political science or sociology it has two noteworthy characteristics: the enormous time-span that is its domain, and the relatively'concrete' nature of its evidence. The great time-span covered by archaeology means that it has a potentially crucial contribution to make to social theory, which is often criticised for being too concerned with structure and not enough with long-term dynamics. Archaeological evidence is'concrete' by comparison with that of, say, sociology since it is typically formed of directly observable objects or traces rather than of statements by or about people. This is clearly both a strength and a weakness.


AUTOMATIC DESCRIPTION AND RECOGNITION OF BOARD PATTERNS IN GO-MOK U

Classics (Collection 2)

A series of computer programs have been written to play the board game Go-Moku. Go-Moku is played on a 19 x 19 square mesh. Player b(w) has a supply of black (white) pieces. The players take it in turns to play a piece on a mesh point. The winner is the first player to complete a 5-pattern, that is, to make up a (horizontal, vertical or diagonal) line of five and only five adjacent pieces of his colour.


Practical machine intelligence

Classics (Collection 2)

Machine intelligence, more commonly known by the misnomer artifical intelligence, is now about twenty-five years old as a scientific field. In contrast with early predictions, its practical applicability has been frustratingly slow to develop. It appears, however, that we are now (finally!) on the verge of practicality in a number of specialities within machine intelligence more or less simultaneously. This can be expected to result in the short term in a qualitative shift in the nature of the field itself, and to result in the longer term in a shift in the way certain industries go about their business. Machine Intelligence Corporation (MIC) was founded in 1978 as a vehicle for bringing the more practical aspects of the field into widespread use.



Report 82-07.pdf

Classics (Collection 2)

This paper describes the student modeler of the GUIDON2 tutor, which understands plan: by a dual search strategy. It first produces multiple predictions of student behavior by a model-driven simulation of the expert. Focused, data-driven searches then explain incongruities. By supplementing each other, these methods lead to an efficient and robust plan understander for a complex domain. Diagnostic problem-solving requires domain knowledge and a plan for applying that knowledge to the problem.



Molecular Scene Analysis: Crystal Structure Determination Through Imagery

Classics (Collection 2)

This chapter describes the design of a prototype knowledge-based system for crystal and molecular structure determination from diffraction data. This system enhances current methods for the determination and interpretation of protein structures by incorporating direct methods probabilistic strategies, experience accumulated in the crystallographic databases, and knowledge representation and reasoning techniques for machine imagery. This paper is based on "Crystal and Molecular Scene Analysis," by Glasgow, Fortier and Allen which appeared in the Proceedings of the Seventh IEEE Conference on Artificial Intelligence Applications, Miami Beach, Florida, Feb. 1991 434 ARTIFICIAL INTELLIGENCE & MOLECULAR BIOLOGY A crystal consists of a regular three-dimensional arrangement of identical building blocks, termed the unit cell; a crystal structure is defined by the disposition of atoms and molecules within this fundamental repeating unit. A given structure is determined by interpretation of an electron-density image of the unit-cell contents which can be generated from the amplitudes and phases of the diffraction data. Normally, however, only the diffraction amplitudes can be measured experimentally: the necessary phase information must be obtained by other means.