"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.

This paper presents a unique real-time obstacle avoidance approach for manipulators and mobile robots based on the artificial potential field concept. Collision avoidance, tradi tionally considered a high level planning problem, can be effectively distributed between different levels of control, al lowing real-time robot operations in a complex environment. This method has been extended to moving obstacles by using a time-varying artificial patential field. We have applied this obstacle avoidance scheme to robot arm mechanisms and have used a new approach to the general problem of real-time manipulator control. We reformulated the manipulator con trol problem as direct control of manipulator motion in oper ational space--the space in which the task is originally described--rather than as control of the task's corresponding joint space motion obtained only after geometric and kine matic transformation.

Stuart J. Russell Department of Computer Science Stanford University Stanford, CA 94305 ABSTRACT In the absence of specific relevance information, the traditional assumption in the study of analogy has been that the most similar analogue is most likely to provide the correct solutions; a justification for this assumption has been lacking, as has any relation between the similarity measure used and the probability of correctness of the analogy. We show how a statistical analysis can be performed to give the probability that a given source will provide a successful analogy, using only the assumption that there are some relevant features somewhere in the source and target descriptions. The predicted variation of the probability with source-target similarity corresponds closely to empirical analogy data obtained by Shepard for human and animal subjects for a wide variety of domains. The utility of analogy by similarity seems to rest on some very fundamental assumptions about the nature of our representations.* I INTRODUCTION Analogical reasoning is usually defined as the argument from known similarities between two things to the existence of further similarities.

To resolve the search-incompleteness of depth-first logic program interpreters, a new interpretation method based on the tabulation technique is developed and modeled as a refinement to SLD resolution. Its search space completeness is proved, and a complete search strategy consisting of iterated stages of depth-first search is presented. It is also proved that for programs defining finite relations only, the method under an arbitrary search strategy is terminating and complete.

(Postscript preprint)Machine Learning, 1(3) 287-316

MIT Press.

We show that the notion of bias in inductive concept learning can be quantified in a way that directly relates to learning performance, and that this quantitative theory of bias can provide guidance in the design of effective learning algorithms. We apply this idea by measuring some common language biases, including restriction to conjunctive concepts and conjunctive concepts with internal disjunction, and, uided by these measurements, develop learning algorithms P or these classes of concepts that have provably good convergence properties. Introduction The theme of this pa er is that the notion of bias in inductive concept learning Ip U86] [R86/ can be quantified in a way that enables us to rove meaningful convergence properties for learning algorit i ms. We measure bias with a combinatorial parameter defined on classes of concepts known as the Vapnik-Chervonenkis dimension (or simply d ensiorr) [VC71/, [P78j', JBEHW86/. The lower the dlmenslon of the class of concepts considered by the learning algorithm, the stronger the bias.

In the last issue of this journal Mitchell, Keller, and Kedar-Cabelli presented a unifying framework for the explanation-based approach to machine learning. While it works well for a number of systems, the framework does not adequately capture certain aspects of the systems under development by the explanation-based learning group at Illinois. The primary inadequacies arise in the treatment of concept operationality, organization of knowledge into schemata, and learning from observation. This paper outlines six specific problems with the previously proposed framework and presents an alternative generalization method to perform explanation-based learning of new concepts.

See also:A Fundamental Tradeoff in Knowledge Representation and Reasoning. Slides. Department of Computer and Information Science. Norwegian University of Science and Technology. IT3706 - Knowledge Representation and Modelling, 2005.Knowledge Representation and Reasoning. Morgan Kaufmann, 2004.Proceedings of the First International Conference on Principles of Knowledge Representation and Reasoning. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 1989.Proceedings of the 2nd International Conference on Principles of Knowledge Representation and Reasoning (1st ed.). James Allen, Ronald J. Brachman, Erik Sandewall, Hector J. Levesque, Ray Reiter, and Richard Fikes (Eds.). Morgan Kaufmann Publishers Inc., San Francisco, CA, USA.Annual Review of Computer Science Vol. 1: 255-287

The paper delineates three different approaches to expert-system development: the low road that involves direct symbolic programming, the high road that involves building a system that contains explicit representation of the knowledge of some matter, and a middle-road system such as Mycin that is between these two extremes. The development of expert systems at Digital Equipment Corporation, Xerox, and Schlumberger is discussed. Perhaps the most valuable portion of the paper is the discussion of the criteria for the selection of an appropriate problem for an expert system. Also of value are the guidelines for managing the stages of development in an expert system. This is a well-written, informative paper that should be required reading for anyone contemplating building an expert system.