Results


Interactive Transfer of Expertise: Acquisition of New Inference Rules

Classics (Collection 2)

ABSTRACT TEntEsuis is a program designed to provide assistance on the task of building knowledge-based systems. It facilitates the interactive transfer of knowledge from a human expert to the system, in a high level dialog conducted in a restricted subset of natural language. TEIRESIAS in operation and demonstrates how it guides the acquisition of new inference rules. I. Introduction Where much early work in artificial intelligence was devoted to the search for a single, powerful, domain-independent problem solving methodology (e.g., This work was supported in part by the Advanced Research Projects Agency under ARPA Order 2494; by a Chaim Weizmann Postdoctoral Fellowship for Scientific Research, and by grant MCS 77-02712 from the National Science Foundation. It was carried out on the SUMEX Computer System, supported by the NIH Grant RR-00785. The program is named for the blind seer in Oedipus the King, since, as we will see, the program, like the prophet, has a form of "higher order" ...


SESSION 1 PAPER 1 SOME METHODS OF ARTIFICIAL INTELLIGENCE AND HEURISTIC PROGRAMMING

Classics (Collection 2)

Marvin Lee Minsky was born in New York on 9th August, 1927. He received his B.A from Harvard in 1950 and Ph.D in Mathematics from Princeton in 1954. For the next three years he was a member of the Harvard University Society of Fellows, and in 1957-58 was staff member of the M.I.T. Lincoln Laboratories. At present he is Assistant Professor of Mathematics at M.I.T. where he is giving a course in Automata and Artificial Intelligence and is also staff member of the Research Laboratory of Electronics. Particular attention is given to processes involving pattern recognition, learning, planning ahead, and the use of analogies or?models!.


Pattern Recognition and Modern Computers

Classics (Collection 2)

Reprinted front the PROCEEDINGS OF THE WESTERN JOINT COMPUTER CONFERENCE Los Angeles, California, March 1955 PRINTED IN THE U.S.A. E CONSIDER the process we call Pattern Recognition. By this we mean the extraction of the significant features of data from a background of irrelevant detail. What we are interested in is simulating this process on digital computers. We give examples on three levels of complexity corresponding to the subjects of the other three speakers here today. We examine in detail the problem on the second level, visual recognition of simple shapes.


Irtellige it S stems

Classics (Collection 2)

We have found out so much, explored old ideas in new ways, given extraordinary new tools to computer programmers, and on and on. At only a half-century old, we can assess AT as successful and productive indeed. Learning is the most important part of artificial intelligence. A basic research effort can explore how to build software that can learn and be educated very broadly. The essence of learning is trying.


GTE Laboratories

Classics (Collection 2)

This document is a GTE Laboratories Technical Report. It describes results and conclusions reached upon completion of a major phase of a research project. The ideas and views put forth by the author have been rev' we accepted by the appropriate Laboratory Director. We explore the use of adaptive components in strategies for playing extremely simple two-person zero-sum games. The adaptation is different from that usually considered in the field of Adaptive Control; rather it is a form of test and gradient descent.


Proceedings of the

Classics (Collection 2)

The Role of Experiences and Examples in Learning Systems Edwina L. Rissland Oliver G. Selfridge Elliot M. Soloway* Department of Computer and Information Science University of Massachusetts Amherst, MA 01003 Abstract In this paper, we discuss the role of experiences and examples in learning systems. We discuss these issues in the context of three systems in particular: Rissland and Soloway's Constrained Example Generation (CEG) System, Selfridge's COUNT, and Soloway's BASEBALL. Examples provide the basis from which generalizations, concepts and conjectures are made. They also provide the criticisms needed to refute and refine. For instance, in Winston's learning program [Winston 1975], examples of the concept to be learned, e.g., an arch, and non-examples, e.g., "near misses", are the critical input from which his program builds a structural description of a concept.


ER10.pdf

Classics (Collection 2)

EXAMPLES AND LEARNING SYSTEMS* Edwina L. Rissland Department of Computer and Information Science University of Massachusetts Amherst, MA 01003, U.S.A. INTRODUCTION Any system that learns or adapts -- whether well-- or ill--defined, man or machine -- must have examples, experiences, and data on which to base its learning or adaptation. Too often, however, the examples that form the basis of learning are taken for granted. This paper will concentrate on the examples as a study in their own right. BACKGROUND The importance of examples to learning systems can be seen in many well--known A.I. programs. For instance, Winston's program [1975] learns the concept of "arch" from a sequence of examples: of arches and non--arches.


20 Three Interactions between Al and Education

Classics (Collection 2)

The understanding of intelligence that has arisen from Al research can be applied to education to significantly enhance learning. The LOGO project, described herein, is based on this premise. Extensions of the LOGO experience are proposed that are based on Al in interesting ways. One extension is to encourage children to write simple AI programs. Tools to aid the child in this endeavor are discussed.


Report 83-47.pdf

Classics (Collection 2)

Edward H. Shortliffe, MD, PhD Division of General Internal Medicine Department of Medicine Stanford University School of Medicine Stanford, California 94305 Dr. Shortlate is recipient of Research Career Development Some notable exceptions occur when specially prepared computer programs are made available by vendors or program committees at annual clinical meetings. Yet this kind of learning tool is seldom used by practicing physicians at other times during the year. In this paper, I would like to consider ways in which computer-based education might be more effectively integrated into the clinical activities of the practicing physician, and to outline some of the technological and psychological barriers to their successful implementation. When physicians reflect on the most intense learning experience of their medical education, they typically focus on the internship year. This "intensity" refers to more than the hours worked and the sleep lost; it is generally recognized that the shee: volume of clinical exposure.


Report 77-09.pdf

Classics (Collection 2)

Used by permission of the International JOint Conference on Artificial Intelligence, Inc.; copies of the Proceedings are available from Morgan Kaufmann Publishers, Inc., 95 First Street, Los Altos, CA 94022, USA. It embodies a particular model of interactive transfer of knowledge from a human expert to the system, and makes possible knowledge transfer in a high level dialog conducted in a restricted subset of natural language. This paper explores an example of TEIRESIAS in operation, and demonstrates how it guides the acquisition of new inference rules. It was carried out on the SUMEX-AM Computer System, supported by the Nil-I under Grant RR-00785. Introduction The knowledge base for a high performance, domain-specific program (e.g., DENDRAL [9], MACSYMA[10]) is traditionally assembled by hand, an ongoing task that typically involves numerous man-years of effort. That is, we have attempted to create an assistant that will help build intelligent programs. The result it: a system called ...