Books in Artificial intelligence expert systems and knowledge based systems

121-130 of 149 results in All results

The KBMT Project

• 1st Edition
• September 25, 1991
• Kenneth Goodman + 1 more
• English
• eBook 978-0-08-051890-9

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

Machine translation of natural languages is one of the most complex and comprehensive applications of computational linguistics and artificial intelligence. This is especially true of knowledge-based machine translation (KBMT) systems, which require many knowledge resources and processing modules to carry out the necessary levels of analysis, representation and generation of meaning and form. The number of real-world problems, tasks, and solutions involved in developing any realistic-size knowledge-based machine translation system is enormous. It is thus difficult for researchers in the field to learn what a system "really does".This book fills that need with a detailed case study of a KBMT system implemented at the Center for Machine Translation at Carnegie Mellon University. The research consists in part of the creation of a system for translation between English and Japanese. The corpora used in the project were manuals for installing and maintaining IBM personal computers (sponsorship by IBM, through its Tokyo Research Laboratory) Individual chapters describe the interlingua texts used in knowledge-based machine translation, the grammar formalism embodied in the system, the grammars and lexicons and their roles in the translation process, the process of source language analysis, an augmentation module that interactively and automatically resolves ambiguities remaining after source language analysis, and the generator, which produces target language sentences. Detailed appendices illustrate the process from analysis through generation.This book is intended for developers, researchers and advanced students in natural language processing and computational linguistics, including all those who have an interest in machine translation and machine-aided translation.

Computational Intelligence, III

• 1st Edition
• July 1, 1991
• G. Valle + 2 more
• English
• eBook 978-0-444-59740-3

  9 7 8 - 0 - 4 4 4 - 5 9 7 4 0 - 3

In recent years AI has been experiencing a deep internal debate on the appropriateness of the symbolic-based paradigm and all of its consequences. While various symbolic representation schemes, as well as their integration, have been proposed, their limitations have continuously pushed researchers for improved versions or entirely new ones. New viewpoints such as the complex dynamic-based approach with neural nets can be regarded simply as new problem solving techniques with specific properties.Under this perspective, what seems to be important is the ability to combine heterogeneous representation and problem-solving techniques. Research on heterogeneous, intelligent systems goes hand in hand with research on specific problem solving methods and paradigms, therefore representing their conceptual and practical glueing element. The papers contained in this proceedings are just one instance of such awareness activity in the international scientific community.

Artificial Intelligence and Computer Vision

• 1st Edition
• June 1, 1991
• Y.A. Feldman + 1 more
• English
• eBook 978-0-444-59928-5

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

Current research in artificial intelligence and computer vision presented at the Israeli Symposium are combined in this volume to present an invaluable resource for students, industry and research organizations. Papers have been contributed from researchers worldwide, showing the growing interest of the international community in the work done in Israel. The papers selected are varied, reflecting the most contemporary research trends.

Machine Learning Proceedings 1991

• 1st Edition
• June 1, 1991
• Lawrence A. Birnbaum + 1 more
• English
• eBook 978-1-4832-9817-7

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

Machine Learning: Proceedings of the Eighth International Workshop (ML91) covers the papers presented at ML91, the Eighth International Workshop on Machine Learning, held at Northwestern University, Evanston, Illinois, USA, in June 1991. The book focuses on constructive induction, learning from theory and data, automated knowledge acquisition, learning in intelligent information retrieval, machine learning in engineering automation, computational models of human learning, and learning reaction strategies. The selection first offers information on design rationale capture as knowledge acquisition, a domain-independent framework for effective experimentation in planning, and knowledge refinement using a high-level, non-technical vocabulary. The text then elaborates on improving the performance of inconsistent knowledge bases via combined optimization method, flexibility of speculative refinement, and a prototype based symbolic concept learning system. Topics include using task descriptions to generate error candidates, functional descriptions of knowledge-based systems, combined optimization method, and inconsistency and related work. The book ponders on learning words from context, modeling the acquisition and improvement of motor skills, a computational model of acquisition for children's addition strategies, and computer modeling of acquisition orders in child language. The manuscript also takes a look at knowledge acquisition combining analytical and empirical techniques; designing integrated learning systems for engineering design; and machine learning for nondestructive evaluation. The selection is highly recommended for researchers interested in machine learning.

Practical Knowledge Engineering

• 1st Edition
• May 13, 1991
• Richard Kelly
• English
• eBook 978-1-4832-9581-7

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

This book provides knowledge engineers with practical methods for initiating, designing, building, managing, and demonstrating successful commercial expert systems. It is a record of what actually works (and does not work) in the construction of expert systems, drawn from the author's decade of experience in building expert systems in all major areas of application for American, European, and Japanese organizations.The book features:* knowledge engineering programming techniques* useful skills for demonstrating expert systems * practical costing and metrics* guidelines for using knowledge representation techniques* solutions to common difficulties in design and implementation

Parallelism and Programming in Classifier Systems

• 1st Edition
• December 1, 1990
• Stephanie Forrest
• English
• eBook 978-0-08-051355-3

  9 7 8 - 0 - 0 8 - 0 5 1 3 5 5 - 3

Parallelism and Programming in Classifier Systems deals with the computational properties of the underlying parallel machine, including computational completeness, programming and representation techniques, and efficiency of algorithms. In particular, efficient classifier system implementations of symbolic data structures and reasoning procedures are presented and analyzed in detail. The book shows how classifier systems can be used to implement a set of useful operations for the classification of knowledge in semantic networks. A subset of the KL-ONE language was chosen to demonstrate these operations. Specifically, the system performs the following tasks: (1) given the KL-ONE description of a particular semantic network, the system produces a set of production rules (classifiers) that represent the network; and (2) given the description of a new term, the system determines the proper location of the new term in the existing network. These two parts of the system are described in detail. The implementation reveals certain computational properties of classifier systems, including completeness, operations that are particularly natural and efficient, and those that are quite awkward. The book shows how high-level symbolic structures can be built up from classifier systems, and it demonstrates that the parallelism of classifier systems can be exploited to implement them efficiently. This is significant since classifier systems must construct large sophisticated models and reason about them if they are to be truly ""intelligent."" Parallel organizations are of interest to many areas of computer science, such as hardware specification, programming language design, configuration of networks of separate machines, and artificial intelligence This book concentrates on a particular type of parallel organization and a particular problem in the area of AI, but the principles that are elucidated are applicable in the wider setting of computer science.

Artificial Intelligence IV

• 1st Edition
• August 12, 1990
• P. Jorrand + 1 more
• English
• eBook 978-1-4832-9778-1

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

Presenting recent results and ongoing research in Artificial Intelligence, this book has a strong emphasis on fundamental questions in several key areas: programming languages, automated reasoning, natural language processing and computer vision.AI is at the source of major programming language design efforts. Different approaches are described, with some of their most significant results: languages combining logic and functional styles, logic and parallel, functional and parallel, logic with constraints.A central problem in AI is automated reasoning, and formal logic is, historically, at the root of research in this domain. This book presents results in automatic deduction, non-monotonic reasoning, non-standard logic, machine learning, and common-sense reasoning. Proposals for knowledge representation and knowledge engineering are described and the neural net challenger to classical symbolic AI is also defended.Finally, AI systems must be able to interact with their environment in a natural and autonomous way. Natural language processing is an important part of this. Various results are presented in discourse planning, natural language parsing, understanding and generation. The autonomy of a machine for perception of its physical environment is also an AI problem and some research in image processing and computer vision is described.

Machine Learning

• 1st Edition
• August 1, 1990
• Yves Kodratoff + 1 more
• English
• eBook 978-0-08-051055-2

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

Machine Learning: An Artificial Intelligence Approach, Volume III presents a sample of machine learning research representative of the period between 1986 and 1989. The book is organized into six parts. Part One introduces some general issues in the field of machine learning. Part Two presents some new developments in the area of empirical learning methods, such as flexible learning concepts, the Protos learning apprentice system, and the WITT system, which implements a form of conceptual clustering. Part Three gives an account of various analytical learning methods and how analytic learning can be applied to various specific problems. Part Four describes efforts to integrate different learning strategies. These include the UNIMEM system, which empirically discovers similarities among examples; and the DISCIPLE multistrategy system, which is capable of learning with imperfect background knowledge. Part Five provides an overview of research in the area of subsymbolic learning methods. Part Six presents two types of formal approaches to machine learning. The first is an improvement over Mitchell's version space method; the second technique deals with the learning problem faced by a robot in an unfamiliar, deterministic, finite-state environment.

Minimalist Mobile Robotics

• 1st Edition
• July 28, 1990
• Jonathan H. Connell
• English
• eBook 978-0-08-051171-9

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

Rather than using traditional artificial intelligence techniques, which are ineffective when applied to the complexities of real-world robot navigaiton, Connell describes a methodology of reconstructing intelligent robots with distributed, multiagent control systems. After presenting this methodology, hte author describes a complex, robust, and successful application-a mobile robot "can collection machine" which operates in an unmodified offifce environment occupied by moving people.

Decentralized A.I

• 1st Edition
• July 6, 1990
• Y. Demazeau + 1 more
• English
• eBook 978-0-444-59924-7

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

Much research in Artificial Intelligence deals with a single agent having complete control over the world. A variation of this is Distributed AI (DAI), which is concerned with the collaborative solution of global problems by a distributed group of entities. This book deals with Decentralized AI (DzAI), which is concerned with the activity of an autonomous agent in a multi-agent world. The word ``agent'' is used in a broad sense, to designate an intelligent entity acting rationally and intentionally with respect to its goals and the current state of its knowledge. A number of these agents coexist and may collaborate with other agents in a common world; each agent may accomplish its own tasks, or cooperate with other agents to perform a personal or global task. The agents have imperfect knowledge about each other and about their common world, which they can update either through perception of the world, or by communication with each other.The papers were originally presented at a workshop held at King's College, Cambridge, and have been revised for this book.