Books in Artificial intelligence expert systems and knowledge based systems

131-140 of 149 results in All results

Computational Intelligence, II

• 1st Edition
• June 1, 1990
• G. Mauri + 2 more
• English
• eBook 978-0-444-59728-1

  9 7 8 - 0 - 4 4 4 - 5 9 7 2 8 - 1

The focus of this volume is ``Heterogeneous Knowledge and Problem Solving Integration'', i.e. the combined use of different knowledge representation and problem solving paradigms.This is a central topic for the design and implementation of problem solving systems, since, from a pragmatic and engineering standpoint, the solution of a large class of problems cannot take place within one single representation language or problem solving paradigm. Heterogeneous systems represent not only a pragmatic answer, but also a theoretical alternative to the homogeneous paradigms.

Readings in Speech Recognition

• 1st Edition
• May 1, 1990
• Alexander Waibel + 1 more
• English
• eBook 978-0-08-051584-7

  9 7 8 - 0 - 0 8 - 0 5 1 5 8 4 - 7

After more than two decades of research activity, speech recognition has begun to live up to its promise as a practical technology and interest in the field is growing dramatically. Readings in Speech Recognition provides a collection of seminal papers that have influenced or redirected the field and that illustrate the central insights that have emerged over the years. The editors provide an introduction to the field, its concerns and research problems. Subsequent chapters are devoted to the main schools of thought and design philosophies that have motivated different approaches to speech recognition system design. Each chapter includes an introduction to the papers that highlights the major insights or needs that have motivated an approach to a problem and describes the commonalities and differences of that approach to others in the book.

Handbook of Human-Computer Interaction

• 1st Edition
• March 28, 1990
• M.G. Helander
• English
• eBook 978-1-4832-9513-8

  9 7 8 - 1 - 4 8 3 2 - 9 5 1 3 - 8

This Handbook is concerned with principles of human factors engineering for design of the human-computer interface. It has both academic and practical purposes; it summarizes the research and provides recommendations for how the information can be used by designers of computer systems. The articles are written primarily for the professional from another discipline who is seeking an understanding of human-computer interaction, and secondarily as a reference book for the professional in the area, and should particularly serve the following: computer scientists, human factors engineers, designers and design engineers, cognitive scientists and experimental psychologists, systems engineers, managers and executives working with systems development.The work consists of 52 chapters by 73 authors and is organized into seven sections. In the first section, the cognitive and information-processing aspects of HCI are summarized. The following group of papers deals with design principles for software and hardware. The third section is devoted to differences in performance between different users, and computer-aided training and principles for design of effective manuals. The next part presents important applications: text editors and systems for information retrieval, as well as issues in computer-aided engineering, drawing and design, and robotics. The fifth section introduces methods for designing the user interface. The following section examines those issues in the AI field that are currently of greatest interest to designers and human factors specialists, including such problems as natural language interface and methods for knowledge acquisition. The last section includes social aspects in computer usage, the impact on work organizations and work at home.

COLT '89

• 1st Edition
• December 25, 1989
• COLT
• English
• eBook 978-0-08-094829-4

  9 7 8 - 0 - 0 8 - 0 9 4 8 2 9 - 4

Computational Learning Theory presents the theoretical issues in machine learning and computational models of learning. This book covers a wide range of problems in concept learning, inductive inference, and pattern recognition. Organized into three parts encompassing 32 chapters, this book begins with an overview of the inductive principle based on weak convergence of probability measures. This text then examines the framework for constructing learning algorithms. Other chapters consider the formal theory of learning, which is learning in the sense of improving computational efficiency as opposed to concept learning. This book discusses as well the informed parsimonious (IP) inference that generalizes the compatibility and weighted parsimony techniques, which are most commonly applied in biology. The final chapter deals with the construction of prediction algorithms in a situation in which a learner faces a sequence of trials, with a prediction to be given in each and the goal of the learner is to make some mistakes. This book is a valuable resource for students and teachers.

Machine Learning Proceedings 1989

• 1st Edition
• June 1, 1989
• Alberto Maria Segre
• English
• eBook 978-1-4832-9740-8

  9 7 8 - 1 - 4 8 3 2 - 9 7 4 0 - 8

Proceedings of the Sixth International Workshop on Machine Learning covers the papers presented at the Sixth International Workshop of Machine Learning, held at Cornell University, Ithaca, New York (USA) on June 26-27, 1989. The book focuses on the processes, methodologies, techniques, and approaches involved in machine learning. The selection first offers information on unifying themes in empirical and explanation-based learning; integrated learning of concepts with both explainable and conventional aspects; conceptual clustering of explanations; and tight integration of deductive and inductive learning. The text then examines multi-strategy learning in nonhomogeneous domain theories; description of preference criterion in constructive learning; and combining case-based reasoning, explanation-based learning, and learning from instruction. Discussions focus on causal explanation of actions, constructive learning, learning in a weak theory domain, learning problem, and individual criteria and their relationships. The book elaborates on learning from plausible explanations, augmenting domain theory for explanation-based generalization, reducing search and learning goal preferences, and using domain knowledge to improve inductive learning algorithms for diagnosis. The selection is a dependable reference for researchers interested in the dynamics of machine learning.

Knowledge Acquisition from Text and Pictures

• 1st Edition
• Volume 58
• April 1, 1989
• H. Mandl + 1 more
• English
• eBook 978-0-08-086712-0

  9 7 8 - 0 - 0 8 - 0 8 6 7 1 2 - 0

Media-didactics have recently become more firmly grounded on cognitive theory, with an increasing concern for the internal processes of knowledge representation and acquisition. With this cognitive aspect in mind, an international group of researchers held a meeting in Tübingen, Federal Republic of Germany, to present and discuss the theoretical approaches to and empirical investigations of knowledge acquisition from text and pictures. This volume contains the revised contributions resulting from that meeting.

Introduction to Machine Learning

• 1st Edition
• March 1, 1989
• Yves Kodratoff
• English
• eBook 978-0-08-050930-3

  9 7 8 - 0 - 0 8 - 0 5 0 9 3 0 - 3

A textbook suitable for undergraduate courses in machine learningand related topics, this book provides a broad survey of the field.Generous exercises and examples give students a firm grasp of theconcepts and techniques of this rapidly developing, challenging subject.Introduction to Machine Learning synthesizes and clarifiesthe work of leading researchers, much of which is otherwise availableonly in undigested technical reports, journals, and conference proceedings.Beginning with an overview suitable for undergraduate readers, Kodratoffestablishes a theoretical basis for machine learning and describesits technical concepts and major application areas. Relevant logicprogramming examples are given in Prolog.Introduction to Machine Learning is an accessible and originalintroduction to a significant research area.

Parallel Processing for Artificial Intelligence 1

• 1st Edition
• Volume 14
• February 12, 1989
• L.N. Kanal + 3 more
• English
• eBook 978-1-4832-9574-9

  9 7 8 - 1 - 4 8 3 2 - 9 5 7 4 - 9

Parallel processing for AI problems is of great current interest because of its potential for alleviating the computational demands of AI procedures. The articles in this book consider parallel processing for problems in several areas of artificial intelligence: image processing, knowledge representation in semantic networks, production rules, mechanization of logic, constraint satisfaction, parsing of natural language, data filtering and data mining. The publication is divided into six sections. The first addresses parallel computing for processing and understanding images. The second discusses parallel processing for semantic networks, which are widely used means for representing knowledge - methods which enable efficient and flexible processing of semantic networks are expected to have high utility for building large-scale knowledge-based systems. The third section explores the automatic parallel execution of production systems, which are used extensively in building rule-based expert systems - systems containing large numbers of rules are slow to execute and can significantly benefit from automatic parallel execution. The exploitation of parallelism for the mechanization of logic is dealt with in the fourth section. While sequential control aspects pose problems for the parallelization of production systems, logic has a purely declarative interpretation which does not demand a particular evaluation strategy. In this area, therefore, very large search spaces provide significant potential for parallelism. In particular, this is true for automated theorem proving. The fifth section considers the problem of constraint satisfaction, which is a useful abstraction of a number of important problems in AI and other fields of computer science. It also discusses the technique of consistent labeling as a preprocessing step in the constraint satisfaction problem. Section VI consists of two articles, each on a different, important topic. The first discusses parallel formulation for the Tree Adjoining Grammar (TAG), which is a powerful formalism for describing natural languages. The second examines the suitability of a parallel programming paradigm called Linda, for solving problems in artificial intelligence.Each of the areas discussed in the book holds many open problems, but it is believed that parallel processing will form a key ingredient in achieving at least partial solutions. It is hoped that the contributions, sourced from experts around the world, will inspire readers to take on these challenging areas of inquiry.

Topics in Expert System Design

• 1st Edition
• Volume 5
• February 12, 1989
• C. Tasso + 1 more
• English
• eBook 978-1-4832-9777-4

  9 7 8 - 1 - 4 8 3 2 - 9 7 7 7 - 4

Expert Systems are so far the most promising achievement of artificial intelligence research. Decision making, planning, design, control, supervision and diagnosis are areas where they are showing great potential. However, the establishment of expert system technology and its actual industrial impact are still limited by the lack of a sound, general and reliable design and construction methodology.This book has a dual purpose: to offer concrete guidelines and tools to the designers of expert systems, and to promote basic and applied research on methodologies and tools. It is a coordinated collection of papers from researchers in the USA and Europe, examining important and emerging topics, methodological advances and practical experience obtained in specific applications. Each paper includes a survey introduction, and a comprehensive bibliography is provided.

Machine Learning Proceedings 1988

• 1st Edition
• December 25, 1988
• John Laird
• English
• eBook 978-1-4832-9769-9

  9 7 8 - 1 - 4 8 3 2 - 9 7 6 9 - 9

Proceedings of the Fifth International Conference 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 10 parts encompassing 49 chapters, this book begins with an overview of the OTIS induction system that learns concepts from positive and negative examples by searching through the space of possible concept descriptions. This text then reviews the methods to selecting examples, and explores the ramifications of one in detail. Other chapters consider a reported phenomenon in machine concept learning wherein concept descriptions can be simplified with little ill-effect on classification accuracy. This book discusses as well an implemented system that learns structural models of shape from noisy image data. The final chapter provides a discussion of the relationship between learning and forgetting. This book is a valuable resource for psychologists, scientists, theorists, and research workers.