In this paper we explore a new theory of discourse structure that stresses the role of purpose and processing in discourse. In this theory, discourse structure is composed of three separate but interrelated components: the structure of the sequence of utterances (called the linguistic structure), a structure of purposes (called the intentional structure), and the state of focus of attention (called the attentional state). The linguistic structure consists of segments of the discourse into which the utterances naturally aggregate. The intentional structure captures the discourse-relevant purposes, expressed in each of the linguistic segments as well as relationships among them. The attentional state is an abstraction of the focus of attention of the participants as the discourse unfolds.

In this article we describe an approach to the construction of a general learning mechanism based on chunking in Soar. Chunking is a learning mechanism that acquires rules from goal-based experience. Soar is a general problem-solving architecture with a rule-based memory. In previous work we have demonstrated how the combination of chunking and Soar could acquire search-control knowledge (strategy acquisition) and operator implementation rules in both search-based puzzle tasks and knowledge-based expert-systems tasks. In this work we examine the anatomy of chunking in Soar and provide a new demonstration of its learning capabilities involving the acquisition and use of macro-operators.

The technology for building knowledge-based systems by inductive inference from examples hasbeen demonstrated successfully in several practical applications. This paper summarizes an approach to synthesizing decision trees that has been used in a variety of systems, and it describes one such system, ID3, in detail. Results from recent studies show ways in which the methodology can be modified to deal with information that is noisy and/or incomplete. A reported shortcoming of the basic algorithm is discussed and two means of overcoming it are compared. The paper concludes with illustrations of current research directionsMachine Learning, 1, p. 81-106

Did you know your Organization can subscribe to the ACM Digital Library?

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.

One of the features of a computer program that attempts concept learning is described by the term bias. The bias of a learning program refers to the collection of factors that are brought to bear upon the selection and consideration of partially formed hypotheses pertaining to the concept being learned. For most learning programs, the bias is fixed and provided by the program's author. Utgoff investigates how a learning program may modify its bias by considering when a shift in bias should be attempted, by proposing a method for accomplishing the shift, and by implementing a program that demonstrates procedures for performing a shift. The book begins with an introduction to machine learning and bias and a discussion of related work.

STRIPS: n. 1) An automated planner by Fikes and Nilsson in 1971 2)

This report contains the following discussions: the defense program simulation of rocky flats plant; spatial representation and reasoning for automated mesh generation; INEL support to modernization efforts at the aberdeen proving ground; artificial intelligence applications at the ICPP; an expert system for tuning particle beam accelerators; quality control expert system; an easily maintained knowledge-based system for interactive delivery of detailed technical information; workload scheduling in DOE production complex; turning operations planning system; a nuclear power plant operator advisor based on artificial intelligence technology; a impact of artificial intelligence on the new production reactor; using expert systems in treaty verification; knowledge-basedmore » systems technology transfer in Oak Ridge; applications of AI to nuclear power plants; knowledge-based computer security systems; robotic grasping of unknown objects: a knowledge-based approach; applying expertise to data in the geologist's assistant expert system; feature recognition based automatic part classification and coding; object-oriented inventories for simulation of manufacturing process; expert system at AWE; plating expert system; inspection process planning expert; troubleshooting local area networks at Savannah River Site; maintenance importance generator; joint theater level simulator; a system for authoring of tutorials including video capture and annotation, links to manuals, and links to executable code; a personal computer based expert system for documenting compliance with the National Environmental Protection Act; spatial representation and reasoning for automated mesh generation; robotic grasping of unknown objects: a knowledge-based approach; and synthesis of engineering anticipatory systems.«

What makes people smarter than computers? These volumes by a pioneering neurocomputing group suggest that the answer lies in the massively parallel architecture of the human mind. They describe a new theory of cognition called connectionism that is challenging the idea of symbolic computation that has traditionally been at the center of debate in theoretical discussions about the mind. The authors' theory assumes the mind is composed of a great number of elementary units connected in a neural network. Mental processes are interactions between these units which excite and inhibit each other in parallel rather than sequential operations.

J. International Computer Chess Association, May, 131–139.