The ability to learn from experience is a fundamental requirement for intelligence. One of the most basic characteristics of human intelligence is that people can learn from problem solving, so that they become more adept at solving problems in a given domain as they gain experience. This book investigates how computers may be programmed so that they too can learn from experience. Specifically, the aim is to take a very general, but inefficient, problem solving system and train it on a set of problems from a given domain, so that it can transform itself into a specialized, efficient problem solver for that domain. on a knowledge-intensive Recently there has been considerable progress made learning approach, explanation-based learning (EBL), that brings us closer to this possibility. As demonstrated in this book, EBL can be used to analyze a problem solving episode in order to acquire control knowledge. Control knowledge guides the problem solver's search by indicating the best alternatives to pursue at each choice point. An EBL system can produce domain specific control knowledge by explaining why the choices made during a problem solving episode were, or were not, appropriate.

This thesis presents an approach to learning good search guiding heuristics for the supposition-based theorom prover E in equational deductions. Search decisions from successful proof searches are represented as sets annotated clause patterns. Term Space Mapping, an alternative learning method for recursive structures is used to learn heuristic evaluation functions for the evaluation of potential new consequences. Experimental results with extended system E/TSM show the success of the approach. Additional contributions of the thesis are an extended superposition calculus and a description of both the proof procedure and the implementation of a state-of-the-art equational theorem prover.

Machine Learning Proceedings 1990

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.

Proceedings of the Fourth International Workshop on Machine Learning provides careful theoretical analyses that make clear contact with traditional problems in machine learning. This book discusses the key role of learning in cognition. Organized into 39 chapters, this book begins with an overview of pattern recognition systems of necessity that incorporate an approximate-matching process to determine the degree of similarity between an unknown input and all stored references. This text then describes the rationale in the Protos system for relegating inductive learning and deductive problem solving to minor roles in support of retaining, indexing and matching exemplars. Other chapters consider the power as well as the appropriateness of exemplar-based representations and their associated acquisition methods. This book discusses as well the extensions to the way a case is classified by a decision tree that address shortcomings. The final chapter deals with the advances in machine learning research. This book is a valuable resource for psychologists, scientists, theorists, and research workers.

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.

Constraint-based reasoning is an important area of automated reasoning in artificial intelligence, with many applications. These include configuration and design problems, planning and scheduling, temporal and spatial reasoning, defeasible and causal reasoning, machine vision and language understanding, qualitative and diagnostic reasoning, and expert systems. Constraint-Based Reasoning presents current work in the field at several levels: theory, algorithms, languages, applications, and hardware. Constraint-based reasoning has connections to a wide variety of fields, including formal logic, graph theory, relational databases, combinatorial algorithms, operations research, neural networks, truth maintenance, and logic programming. The ideal of describing a problem domain in natural, declarative terms and then letting general deductive mechanisms synthesize individual solutions has to some extent been realized, and even embodied, in programming languages. Contents Introduction, E. C. Freuder, A. K. Mackworth * The Logic of Constraint Satisfaction, A. K. Mackworth * Partial Constraint Satisfaction, E. C. Freuder, R. J. Wallace * Constraint Reasoning Based on Interval Arithmetic: The Tolerance Propagation Approach, E. Hyvonen * Constraint Satisfaction Using Constraint Logic Programming, P. Van Hentenryck, H. Simonis, M. Dincbas * Minimizing Conflicts: A Heuristic Repair Method for Constraint Satisfaction and Scheduling Problems, S. Minton, M. D. Johnston, A. B. Philips, and P. Laird * Arc Consistency: Parallelism and Domain Dependence, P. R. Cooper, M. J. Swain * Structure Identification in Relational Data, R. Dechter, J. Pearl * Learning to Improve Constraint-Based Scheduling, M. Zweben, E. Davis, B. Daun, E. Drascher, M. Deale, M. Eskey * Reasoning about Qualitative Temporal Information, P. van Beek * A Geometric Constraint Engine, G. A. Kramer * A Theory of Conflict Resolution in Planning, Q. Yang A Bradford Book.