This research monograph describes the integration of analogical and case-based reasoning into general problem solving and planning as a method of speedup learning. The method, based on derivational analogy, has been fully implemented in PRODIGY/ANALOGY and proven in practice to be amenable to scaling up, both in terms of domain and problem complexity. In this work, the strategy-level learning process is cast for the first time as the automation of the complete cycle of construction, storing, retrieving, and flexibly reusing problem solving experience. The algorithms involved are presented in detail and numerous examples are given. Thus the book addresses researchers as well as practitioners.

The ability to learn is one of the most fundamental attributes of intelligent behavior. Consequently, progress in the theory and computer modeling of learn ing processes is of great significance to fields concerned with understanding in telligence. Such fields include cognitive science, artificial intelligence, infor mation science, pattern recognition, psychology, education, epistemology, philosophy, and related disciplines. The recent observance of the silver anniversary of artificial intelligence has been heralded by a surge of interest in machine learning-both in building models of human learning and in understanding how machines might be endowed with the ability to learn. This renewed interest has spawned many new research projects and resulted in an increase in related scientific activities. In the summer of 1980, the First Machine Learning Workshop was held at Carnegie-Mellon University in Pittsburgh. In the same year, three consecutive issues of the Inter national Journal of Policy Analysis and Information Systems were specially devoted to machine learning (No. 2, 3 and 4, 1980). In the spring of 1981, a special issue of the SIGART Newsletter No. 76 reviewed current research projects in the field. . This book contains tutorial overviews and research papers representative of contemporary trends in the area of machine learning as viewed from an artificial intelligence perspective. As the first available text on this subject, it is intended to fulfill several needs.

Machine Learning Methods for Planning provides information pertinent to learning methods for planning and scheduling. This book covers a wide variety of learning methods and learning architectures, including analogical, case-based, decision-tree, explanation-based, and reinforcement learning. Organized into 15 chapters, this book begins with an overview of planning and scheduling and describes some representative learning systems that have been developed for these tasks. This text then describes a learning apprentice for calendar management. Other chapters consider the problem of temporal credit assignment and describe tractable classes of problems for which optimal plans can be derived. This book discusses as well how reactive, integrated systems give rise to new requirements and opportunities for machine learning. The final chapter deals with a method for learning problem decompositions, which is based on an idealized model of efficiency for problem-reduction search. This book is a valuable resource for production managers, planners, scientists, and research workers.

This handbook is an essential, comprehensive resource for students and academics interested in topics in cognitive psychology, including perceptual issues, attention, memory, knowledge representation, language, emotional influences, judgment, problem solving, and the study of individual differences in cognition.

The biennial International Conference on Case-Based Reasoning (ICCBR) - ries, which began in Sesimbra, Portugal, in 1995, was intended to provide an international forum for the best fundamental and applied research in case-based reasoning (CBR). It was hoped that such a forum would encourage the g- wth and rigor of the eld and overcome the previous tendency toward isolated national CBR communities. The foresight of the original ICCBR organizers has been rewarded by the growth of a vigorous and cosmopolitan CBR community. CBR is now widely recognized as a powerful and important computational technique for a wide range of practical applications. By promoting an exchange of ideas among CBR researchers from across the globe, the ICCBR series has facilitated the broader acceptance and use of CBR. ICCBR-99 has continued this tradition by attracting high-quality research and applications papers from around the world. Researchers from 21 countries submitted 80 papers to ICCBR-99. From these submissions, 17 papers were selected for long oral presentation, 7 were accepted for short oral presentation, and 19 papers were accepted as posters. This volume sets forth these 43 papers, which contain both mature work and innovative new ideas.

Wide aspects of a university education address design: the conceptualization, planning and implementation of man-made artifacts. All areas of engineering, parts of computer science and of course architecture and industrial design all claim to teach design. Yet the education of design tends ot follow tacit practices, without explicit assumptions, goals and processes. This book is premised on the belief that design education based on a cognitive science approach can lead to significant improvements in the effectiveness of university design courses and to the future capabilities of practicing designers. This applies to all professional areas of design. The book grew out of publications and a workshop focusing on design education. This volume attempts to outline a framework upon which new efforts in design education might be based. The book includes chapters dealing with six broad aspects of the study of design education: • Methodologies for undertaking studies of design learning • Longitudinal assessment of design learning • Methods and cases for assessing beginners, experts and special populations • Studies of important component processes • Structure of design knowledge • Design cognition in the classroom

In the last few years, there has been an enormous amount of activity in the study of analogy and metaphor. This is partly because of an interest of artificial intelligence researchers in simulating learning processes using analogy. It also arises from critical examinations of standard theories in the philosophy of language, with their inbuilt literal/meta phoric distinction. This volume consists of recent previously unpub lished work in this area, with a particular emphasis upon the role of analogies in reasoning and, more generally, their role in thought and language. The papers are contributed by philosophers, computer scientists, cognitive scientists and literary critics. Researchers in these fields whose focus is the study of analogy and metaphor will find much of interest in this volume. These essays can also serve as an introduction to some of the major approaches taken in the investigation of analogy. As noted, this volume brings together the work of researchers in several different disciplines. The various approaches taken with respect to the understanding of analogy tend to be rather different, however, the articles suggest a common conclusion. Analogy and metaphor pervade thought and language; their close investigation thus constitutes a valuable contribution to our understanding of persons. DAVID H. HELMAN Case Western Reserve University vii PART I CONCEPTUAL AND CATEGORICAL THEORIES OF ANALOGICAL UNDERSTANDING MARK TURNER CATEGORIES AND ANALOGIES I want to pursue the following claims: The way we categorize helps explain the way we recognize a statement as an analogy.