Complex Systems, 1 (5), 995-1019.

In this article, we present a programming language for expressing classificatory problem solvers. CSRL (Conceptual Structures Representation Language) provides structures for representing classification trees, for navigating within those trees, and for encoding uncertainly judgments about the presence of hypotheses. We discuss the motivations, theory, and assumptions that underlie CRSL. Also, some expert systems constructed with CSRL are briefly described.

This report describes recent and continuing research in artificial intelligence and related fields being conducted at the University of Pennsylvania. Although AI research takes place primarily in the Department of Computer and Information Science ( in School of Engineering and Applied Science), many aspects of this research are preformed in collaboration with other engineering departments as well as other schools at the University, such as the College of Arts and Sciences, the School of Medicine, and Wharton School.

In fact, such a pattern can itself be considered a frame, where the position of each pixel is a slot, and the shade or A recent article by Ronald Brachman (Brachman, color at each pixel is then the attached value. It should 1985) points out some philosophical or semantic problems then be possible to represent this pattern as I have just in using the notion of a prototype, which is described by described it-z.e., by a frame representing the background, using default properties. The problem arises since default partially obscured or covered by a frame representing the properties can be overridden or cancelled in representing object of interest, partially obscured or covered by some particular instances, and therefore lack definitional power: other objects. The fact that some part of the object of interest is obscured does not mean that it is no longer there, nor As an example, Brachman presents an elephant joke: that it is not intrinsic to the object's definition. Q: What's big and gray, has a trunk, and lives in the trees?

See also: Evaluating influence diagrams with decision circuits. In Proceedings of the Twenty-Third Conference on Uncertainty in Artificial Intelligence (UAI2007)Operations Research, 34, 871-882

"The problem of formulating general concepts from specific training examples has long been a major focus of machine learning research. While most previous research has focused on empirical methods for generalizing from a large number of training examples using no domain-specific knowledge, in the past few years new methods have been developed for applying domain-specific knowledge to formulate valid generalizations from single training examples. The characteristic common to these methods is that their ability to generalize from a single example follows from their ability to explain why the training example is a member of the concept being learned. This paper proposes a general, domain-independent mechanism, called EBG, that unifies previous approaches to explanation-based generalization. The EBG method is illustrated in the context of several example problems, and used to contrast several existing systems for explanation-based generalization. The perspective on explanation-based generalization afforded by this general method is also used to identify open research problems in this area." Machine Learning, 1 (1), 47–80.

In PODS-86, pp. 1–16

See also: 2005 AAAI Classic Paper Awards summary of significance by Tom Mitchell in AI Magazine 26(4), 2005.Proc. AAAI-86

MIT Press.

Artificial Intelligence, 29, 241–288.