Recently published
Natural Language Processing and Knowledge Representation
Language for Knowledge and Knowledge for Language
Edited by Lucja M. Iwanska and Stuart C. Shapiro
Natural language refers to human language–complex, irregular, diverse, with all its philosophical problems of meaning and context. Setting a new direction in AI research, this book explores the development of knowledge representation and reasoning systems that take seriously the role of natural language in human information and knowledge processing.
Traditionally, knowledge representation and reasoning systems have incorporated natural language as interfaces to expert systems or knowledge bases that performed tasks separate from natural language processing. As this book shows, however, the computational nature of representation and inference in natural language makes it the ideal model for all tasks in an intelligent computer system. Natural language processing combines the qualitative characteristics of human knowledge processing with a computer’s quantitative advantages, allowing for an in-depth, systematic processing of vast amounts of information. The essays in this interdisciplinary book cover a range of implementations and designs, from formal computational models to large-scale natural language processing systems.
ISBN 0-262-59021-2 470 pp., illus., bibliography, index
$40.00 softcover Copublished by The MIT Press
Advances in Distributed and Parallel Knowledge Discovery
Edited by Hillol Kargupta and Philip Chan
Knowledge discovery and data mining (KDD) deals with the problem of extracting interesting associations, classifiers, clusters, and other patterns from data. The emergence of network-based distributed computing environments has introduced an important new dimension to this problem–distributed sources of data. Traditional centralized KDD typically requires central aggregation of distributed data, which may not always be feasible because of limited network bandwidth, security concerns, scalability problems, and other practical issues. Distributed knowledge discovery (DKD) works with the merger of communication and computation by analyzing data in a distributed fashion. This technology is particularly useful for large heterogeneous distributed environments such as the Internet, intranets, mobile computing environments, and sensor-networks. When the datasets are large, scaling up the speed of the KDD process is crucial. Parallel knowledge discovery (PKD) techniques address this problem by using high performance multi-processor machines. This book presents introductions to DKD and PKD, extensive reviews of the field, and state-of-the-art techniques.
ISBN 0-262-61155-4 472 pp., illus., bibliography, index
$45.00 softcover Copublished by The MIT Press
Software Agents
Edited by Jeffrey M. Bradshaw
Following introductory pieces authored by well-known proponents (and a critic) of agent approaches, this book contains a set of chapters describing how agents have been used to enhance learning and provide intelligent assistance to users in situations where direct manipulation interfaces alone are insufficient. It also contains writings detailing various approaches to agent-to-agent communication and agent mobility, as well as the use of agents to provide intelligent interoperability between loosely-coupled components of distributed systems.
The chapters are authored by the leading researchers and developers of agent-based systems. They not only summarize the state-of-the-art, but point the way in which standards and products incorporating agent technology are likely to evolve over the next few years. Because of the wide variety of issues and approaches addressed, this resource is ideal for classroom use as well as computing professionals. Because the book describes basic concepts and implementations without resorting to mathematical or overly technical terms, it will also be suitable for many noncomputing professionals who are interested in a survey of this rapidly growing field.
ISBN 0-262-52234-9 490 pp., illus., bibliography, index
$45.00 softcover Copublished by The MIT Press
Artificial Intelligence and Mobile Robots
Case Studies of Successful Robot Systems
Edited by David Kortenkamp, R. Peter Bonasso, and Robin Murphy
This book contains thirteen case studies of successful mobile robot systems representing the best available implementations by leading universities and research laboratories. These are not robots that simply work in the laboratory under constrained conditions. They have left the lab and been tested in natural and unknown environments. Many common themes are apparent throughout the book including navigation and mapping, computer vision, and architecture. Each case study is self-contained and describes a complete robot system, including detailed descriptions of important algorithms, and pseudocode. This book serves as a recipe book for designing successful mobile robot applications. The final case studies in this book describe an approach to using mobile robots in the classroom.
ISBN 0-262-61137-6 400 pp., illus., bibliography, index
$45.00 softcover Copublished by The MIT Press
COPYRIGHT 2001 American Association for Artificial Intelligence
COPYRIGHT 2002 Gale Group
