Applying Case-Based Reasoning: Techniques for Enterprise System, by Ian
Watson, Morgan Kaufman, 200 pages, $44.95, ISBN 1-55860-462-6
Case-based reasoning (CBR) is one of the most promising industrial
applications of AI, having already been successfully implemented for
applications such as customer support, quality assurance, aircraft
maintenance, process planning, and decision support -- and many more
applications are achievable. In the many fields where case records are
routinely maintained, the cost of automating processes such as design,
diagnosis and scheduling can be easily justified by the subsequent gains in
efficiency.
CBR has the additional advantage of being relatively simple to implement,
as this book demonstrates. The author explains the principles of CBR for an
industrial audience, describing the field's origins and contrasting it with
mainstream information disciplines. Through case studies and step-by-step
examples, the book shows the reader how to design and implement a reliable,
robust CBR system in a real-world environment.
Additional resources are provided in a survey of commercially available CBR
tools, a comprehensive bibliography, and a listing of companies providing
CBR software and services.
Watson is with the University of Salford.
Mind as Motion: Explorations in the Dynamics of Cognition, edited by Robert
F. Port and Timothy van Gelder, A Bradford Book, 590 pages, $30, ISBN
0-262-66110-1
This book is a comprehensive presentation of the dynamical approach to
cognition. It contains a representative sampling of original, current
research on topics such as perception, motor control, speech and language,
decision making, and development. Included are chapters by pioneers of the
approach, as well as others applying the tools of dynamics to a wide range
of new problems. Throughout, particular attention is paid to the
philosophical foundations of this new research program.
Cognitive science has traditionally been dominated by an AI-based
computational paradigm, in which cognition is taken to be the manipulation
of internal symbols. Even as the potential of this paradigm continues to be
explored, limitations are becoming increasingly apparent. Researchers
throughout cognitive science have been casting around for alternative
theoretical frameworks.
Out of this flux has emerged the dynamical concept, according to which
cognitive processes are behavioral patterns of non-linear dynamical systems
and are best studied using the mathematics of dynamical modeling and
dynamical systems theory.
The book provides a conceptual and historical overview of the dynamical
approach, a tutorial introduction to dynamics for cognitive scientists, and
a glossary covering the most frequently used terms. Each chapter includes
an introduction by the editors, outlining its main ideas and placing it in
context, and a guide to further reading.
Port is with Indiana University, and van Gelder is with the University of
Melbourne (Australia).
Readings in Intelligent User Interfaces, edited by Mark Maybury and
Wolfgang Wahlster, Morgan Kaufman, 736 pages, $59.95, ISBN 1-55860-444-8
The research and development of intelligent user interfaces has assumed
heightened importance with the rapid increase of on-line information and
the expanding complexity of computer applications. This book concentrates
on intelligent knowledge-based user interfaces, specifically focusing on a
combination of spoken language, natural language processing, and multimedia
and multimodal processing.
The sections of this book include editorial introductions to the topic and
papers.
Maybury is with Mitre Corp., and Wahlster is with German Research Center
for AI.
On the Origin of Objects, by Brian Cantwell Smith, A Bradford Book, 420
pages, $17.50, ISBN 0-262-69209-0
This book is the culmination of the author's decade-long investigation into
the philosophical and metaphysical foundations of computation, AI and
cognitive science. Based on a sustained critique of the formal tradition
that underlies the reigning views, he presents an argument for an embedded,
participatory, "irreductionist," metaphysical alternative. The author seeks
to revise our understanding not only of the machines we build but also of
the world with which they interact.
Smith's project begins as a search for a comprehensive theory of
computation, able to do empirical justice to practice and conceptual
justice to the computational theory of mind. A rigorous commitment to these
two criteria ultimately leads him to recommend a radical overhaul of our
traditional conception of metaphysics.
Along the way, Smith offers many ideas: the distinction between
particularity and individuality; the methodological notion of an
"inscription error"; an argument that there are no individuals within
physics; various deconstructions of the type-instance distinction; an
analysis of formality as overly disconnected ("discreteness run amok"); a
conception of the boundaries of objects as properties of unruly
interactions between objects and subjects; an argument for the theoretical
centrality of reference preservation; and a theatrical, acrobatic metaphor
for the contortions involved in the preservation of reference and resultant
stabilization of objects.
Smith is with Indiana University.
|