A fundamental assumption of work in artificial intelligence and machine learning is that knowledge is expressed in a computer with the help of knowledge representations. Since the proper choice of such representations is a difficult task that fundamentally affects the capabilities of a system, the problem of automatic representation change is an important topic in current research. Concept Formation and Knowledge Revision focuses on representation change as a concept formation task, regarding concepts as the elementary representational vocabulary from which further statements are constructed. Taking an interdisciplinary approach from psychological foundations to computer implementations, the book draws on existing psychological results about the nature of human concepts and concept formation to determine the scope of concept formation phenomena, and to identify potential components of computational concept formation models. The central idea of this work is that computational concept formation can usefully be understood as a process that is triggered in a demand-driven fashion by the representational needs of the learning system, and identify the knowledge revision activities of a system as a particular context for such a process. The book presents a detailed analysis of the revision problem for first-order clausal theories, and develops a set of postulates that any such operation should satisfy. It shows how a minimum theory revision operator can be realized by using exception sets, and that this operator is indeed maximally general. The book then shows that concept formation can be triggered from within the knowledge revision process whenever the existing representation does not permit the plausible reformulation of an exception set, demonstrating the usefulness of the approach both theoretically and empirically within the learning knowledge acquisition system MOBAL. In using a first-order representation, this book is part of the rapidly developing field of Inductive Logic Programming (ILP). By integrating the computational issues with psychological and fundamental discussions of concept formation phenomena, the book will be of interest to readers both theoretically and psychologically inclined. From the foreword by Katharina Morik: ` The ideal to combine the three sources of artificial intelligence research has almost never been reached. Such a combined and integrated research requires the researcher to master different ways of thinking, different work styles, different sets of literature, and different research procedures. It requires capabilities in software engineering for the application part, in theoretical computer science for the theory part, and in psychology for the cognitive part. The most important capability for artificial intelligence is to keep the integrative view and to create a true original work that goes beyond the collection of pieces from different fields. This book achieves such an integrative view of concept formation and knowledge revision by presenting the way from psychological investigations that indicate that concepts are theories and point at the important role of a demand for learning. to an implemented system which supports users in their tasks when working with a knowledge base and its theoretical foundation. '

This is the tenth volume in a series on information modelling and knowledge bases. The topics of the articles cover a wide variety of themes in the domain of information modelling, design and specification of information systems and knowledge bases, ranging from foundations and theories to systems construction and application studies. The contributions in this volume represent the following major themes: models in intelligent activity; concept modelling and conceptual modelling; conceptual modelling and information requirements specification; collections of concepts, knowledge base design, and database design; human-computer interaction and modelling; software engineering and modelling; and applications.

Multistrategy learning is one of the newest and most promising research directions in the development of machine learning systems. The objectives of research in this area are to study trade-offs between different learning strategies and to develop learning systems that employ multiple types of inference or computational paradigms in a learning process. Multistrategy systems offer significant advantages over monostrategy systems. They are more flexible in the type of input they can learn from and the type of knowledge they can acquire. As a consequence, multistrategy systems have the potential to be applicable to a wide range of practical problems. This volume is the first book in this fast growing field. It contains a selection of contributions by leading researchers specializing in this area. See below for earlier volumes in the series.

The design of knowledge systems is finding myriad applications from corporate databases to general decision support in areas as diverse as engineering, manufacturing and other industrial processes, medicine, business, and economics. In engineering, for example, knowledge bases can be utilized for reliable electric power system operation. In medicine they support complex diagnoses, while in business they inform the process of strategic planning. Programmed securities trading and the defeat of chess champion Kasparov by IBM's Big Blue are two familiar examples of dedicated knowledge bases in combination with an expert system for decision-making.With volumes covering "Implementation," "Optimization," "Computer Techniques," and "Systems and Applications," this comprehensive set constitutes a unique reference source for students, practitioners, and researchers in computer science, engineering, and the broad range of applications areas for knowledge-based systems.

In Order to Learn shows how order effects are crucial in human learning, instructional design, machine learning, and both symbolic and connectionist cognitive models. Each chapter explains a different aspect of how the order in which material is presented can strongly influence what is learned by humans and theoretical models of learning in a variety of domains. In addition to data, models are provided that predict and describe order effects and analyze how and when they will occur.

This book constitutes the refereed proceedings of the 10th International Conference on Algorithmic Learning Theory, ALT'99, held in Tokyo, Japan, in December 1999. The 26 full papers presented were carefully reviewed and selected from a total of 51 submissions. Also included are three invited papers. The papers are organized in sections on Learning Dimension, Inductive Inference, Inductive Logic Programming, PAC Learning, Mathematical Tools for Learning, Learning Recursive Functions, Query Learning and On-Line Learning.

This volume constitutes the refereed proceedings of the 4th Pacific Rim International Conference on Artificial Intelligence, PRICAI '96, held in Cairns, Queensland, Australia in August 1996. The 56 revised full papers included in the book were carefully selected for presentation at the conference from a total of 175 submissions. The topics covered are machine learning, interactive systems, knowledge representation, reasoning about change, neural nets and uncertainty, natural language, constraint satisfaction and optimization, qualitative reasoning, automated deduction, nonmonotonic reasoning, intelligent agents, planning, and pattern recognition.