By Raymond J. Mooney.

Extending Explanation-Based Learning by Generalizing the Structure of Explanations presents several fully-implemented computer systems that reflect theories of how to extend an interesting subfield of machine learning called explanation-based learning. This book discusses the need for generalizing explanation structures, relevance to research areas outside machine learning, and schema-based problem solving. The result of standard explanation-based learning, BAGGER generalization algorithm, and empirical analysis of explanation-based learning are also elaborated. This text likewise covers the effect of increased problem complexity, rule access strategies, empirical study of BAGGER2, and related work in similarity-based learning. This publication is suitable for readers interested in machine learning, especially explanation-based learning.

Explanation-Based Learning (EBL) can generally be viewed as substituting background knowledge for the large training set of exemplars needed by conventional or empirical machine learning systems. The background knowledge is used automatically to construct an explanation of a few training exemplars. The learned concept is generalized directly from this explanation. The first EBL systems of the modern era were Mitchell's LEX2, Silver's LP, and De Jong's KIDNAP natural language system. Two of these systems, Mitchell's and De Jong's, have led to extensive follow-up research in EBL. This book outlines the significant steps in EBL research of the Illinois group under De Jong. This volume describes theoretical research and computer systems that use a broad range of formalisms: schemas, production systems, qualitative reasoning models, non-monotonic logic, situation calculus, and some home-grown ad hoc representations. This has been done consciously to avoid sacrificing the ultimate research significance in favor of the expediency of any particular formalism. The ultimate goal, of course, is to adopt (or devise) the right formalism.

Brings together a diversity of research on goal-driven learning to establish a broad, interdisciplinary framework that describes the goal-driven learning process. In cognitive science, artificial intelligence, psychology, and education, a growing body of research supports the view that the learning process is strongly influenced by the learner's goals. The fundamental tenet of goal-driven learning is that learning is largely an active and strategic process in which the learner, human or machine, attempts to identify and satisfy its information needs in the context of its tasks and goals, its prior knowledge, its capabilities, and environmental opportunities for learning. This book brings together a diversity of research on goal-driven learning to establish a broad, interdisciplinary framework that describes the goal-driven learning process. It collects and solidifies existing results on this important issue in machine and human learning and presents a theoretical framework for future investigations. The book opens with an an overview of goal-driven learning research and computational and cognitive models of the goal-driven learning process. This introduction is followed by a collection of fourteen recent research articles addressing fundamental issues of the field, including psychological and functional arguments for modeling learning as a deliberative, planful process; experimental evaluation of the benefits of utility-based analysis to guide decisions about what to learn; case studies of computational models in which learning is driven by reasoning about learning goals; psychological evidence for human goal-driven learning; and the ramifications of goal-driven learning in educational contexts. The second part of the book presents six position papers reflecting ongoing research and current issues in goal-driven learning. Issues discussed include methods for pursuing psychological studies of goal-driven learning, frameworks for the design of active and multistrategy learning systems, and methods for selecting and balancing the goals that drive learning. A Bradford Book

Machine Learning Proceedings 1988

Volumes 21 and 22 of Advances in Chemical Engineering contain ten prototypical paradigms which integrate ideas and methodologies from artificial intelligence with those from operations research, estimation andcontrol theory, and statistics. Each paradigm has been constructed around an engineering problem, e.g. product design, process design, process operations monitoring, planning, scheduling, or control. Along with the engineering problem, each paradigm advances a specific methodological theme from AI, such as: modeling languages; automation in design; symbolic and quantitative reasoning; inductive and deductive reasoning; searching spaces of discrete solutions; non-monotonic reasoning; analogical learning;empirical learning through neural networks; reasoning in time; and logic in numerical computing. Together the ten paradigms of the two volumes indicate how computers can expand the scope, type, and amount of knowledge that can be articulated and used in solving a broad range of engineering problems. Sets the foundations for the development of computer-aided tools for solving a number of distinct engineering problems Exposes the reader to a variety of AI techniques in automatic modeling, searching, reasoning, and learning The product of ten-years experience in integrating AI into process engineering Offers expanded and realistic formulations of real-world problems

The ability to learn is a fundamental characteristic of intelligent behavior. Consequently, machine learning has been a focus of artificial intelligence since the beginnings of AI in the 1950s. The 1980s saw tremendous growth in the field, and this growth promises to continue with valuable contributions to science, engineering, and business. Readings in Machine Learning collects the best of the published machine learning literature, including papers that address a wide range of learning tasks, and that introduce a variety of techniques for giving machines the ability to learn. The editors, in cooperation with a group of expert referees, have chosen important papers that empirically study, theoretically analyze, or psychologically justify machine learning algorithms. The papers are grouped into a dozen categories, each of which is introduced by the editors.