"A program that achieves the interpretation of line drawings as polyhedral scenes is described. The method is based on general coherence rules that the surfaces and edges must satisfy, thereby avoiding the use of predetermined interpretations of particular categories of picture junctions and corners." The paper also comments on the relationship of this program to four other scene analysis programs.In IJCAI-73: THIRD INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 20-23 August 1973, Stanford University Stanford, California. Revised version in Artificial Intelligence 4:121-137.

L. Peter Deutsch Xerox corporation, Palo Alto Research center (PARC) Palo Alto, California 94304 Abstract This paper presents a machine designed for compact representation and rapid execution of LISP programs. The machine language is a factor of 2 to 5 more compact than S-expressions or conventional compiled code, and the.compiler is extremely simple. The encoding scheme is potentially applicable to data as well as program. The machine also provides for user-defined data structures. Introduction Pew existing computers permit convenient or efficient implementation of dynamic storage allocation, recursive procedures, or operations on data whose type is represented explicitly at run time rather than determined at compile time. This mismatch between machine and language design plagues every implementor of languages designed for manipulation of structured information.

This paper describes the structure and operation of the Hearsay speech understanding system by the use of a specific example illustrating the various stages of recognition. The system consists of a set of cooperating independent processes, each representing a source of Knowledge. The knowledge is used either to predict what may appear in a given context or to verify hypotheses resulting from a prediction. The structure of the system is illustrated by considering its Operation in a particular task situation: Voice-Chess. The representation and use of various sources of knowledge are outlined. Preliminary results of the reduction in search resulting from the use of various sources of knowledge are given.See also: IEEE Transactions on Computers C-25:427-431.(1976).In IJCAI-73: THIRD INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 20-23 August 1973, Stanford University Stanford, California.

ON THE MECHANIZATION OF ABDUCTIVE LOGIC Harry E. Pople, Jr. Graduate School of Business University of Pittsburgh Pittsburgh, Pennsylvania 15260 Session 6 Logic: II Theorem Proving and Abstract Abduction Is a basic form of logical inference, which is said to engender the use of plans, perceptual models, intuitions, and analogical reasoning - all aspects of Intelligent behavior that have so far failed to find representation in existing formal deductive systems. This paper explores the abductive reasoning process and develops a model for its mechanization, .which An application of the method to the problem of medical diagnosis is discussed. Introduction There has been growing criticism lately concerning the methodology of artificial intelligence. While differing in the specifics of their analyses of the problem, most thoughtful observers seem to feel that the current stock of deductive machinery is simply not up to the task at hand.

Eugene, Oregon: Condon Lecture Publications, 1973. Also MIT Al Laboratory, memo 252.

in Roger Schank and Kenneth Colby (eds), Computer Models of Thought and Language, pp. 187-247, San Francisco: W. H. Freeman and Co., 1973

For the past several years research on robot problem-solving methods has centered on what may one day be called'simple' plans: linear sequences of actions to be performed by single robots to achieve single goals in static environments. Recent speculation and preliminary work at several research centers has suggested a variety of ways in which these traditional constraints could be relaxed. In this paper we describe some of these possible extensions, illustrating the discussion where possible with examples taken from the current Stanford Research Institute robot system.

BBN Rep. No. 2378, Bolt Beranek and Newman, Inc., Cambridge, Mass.

The study of perception is divided among many established sciences: physiology, experimental psychology and machine intelligence; with several others making contributions. But each of the contributing sciences tends to have its own concepts, and ways of considering problems. Each -- to use T. S. Kuhn's term (1962) -- has its own'paradigm', within which its science is respectable. This can make cooperation difficult, as misunderstandings (and even distrust) can be generated by paradigm differences. This paper is a plea to consider perceptual phenomena from many points of view, and to consider whether a general paradigm for perception might be found.

The intention is as follows.