Traditional artificial
intelligence and neural networks are
generally considered appropriate for
solving different types of problems. On
the surface these two approaches appear
to be very different, but a growing body
of current research is focused on how the
strengths of each can be incorporated
into the other and built into systems
that include the best features of both.
Artificial Intelligence and Neural
Networks: Steps Toward Principled
Integration is a critical examination of
the key issues, underlying assumptions
and suggestions related to the
reconciliation and principled integration
of artificial intelligence and neural
networks. With contributions from leading
researchers in the field, this
comprehensive text provides a thorough
introduction to the basics of symbol
processing, connectionist networks and
their integration. Numerous examples of
the integration of artificial
intelligence and neural networks for a
variety of specific applications provide
unique insight into this evolving area.
Preface
Introduction:
Artificial Intelligence and
Neural Networks: Steps Toward
Principled Integration. Leonard
Uhr & Vasant Honavar
Chapter
I: Horses of a Different Color?
Margaret Boden
Chapter
II: Architecture of Intelligence:
The Problems and Current
Approaches to Solutions. B.
Chandrasekaran & Susan G.
Josephson
Chapter
III: Schema Theory: Cooperative
Computation for Brain Theory and
Distributed AI. Michael Arbib
Chapter
IV: The Role of
Inter-disciplinary Research
Involving Neuroscience in the
Development of Intelligent
Systems. Thomas M. McKenna
Chapter
V: Why the Difference Between
Connectionism and Anything Else
is More Than You Might Think but
Less Than You Might Hope. Gregg
C. Oden
Chapter
VI: Beyond Symbolic: Prolegomena
to a Kama-Sutra of
Compositionality. Timothy van
Gelder & Robert Port
Chapter
VII: How Might Connectionist
Systems Represent Propositional
Attitudes? John A. Barnden
Chapter
VIII: Three Horns of the
Representational Trilemma. Noel
A. Sharkey & Stuart A.
Jackson
Chapter
IX: Learned Categorical
Perception in Neural nets:
Implications for Symbol
Grounding. Steven Harnad, Stephen
J. Hanson & Joseph Lubin
Chapter
X: Image and Symbol: Continuous
Computation and the Emergence of
The Discrete. Bruce J. MacLennan
Chapter
XI: Graded State Machines: The
Representation of Temporal
Contingencies in Simple Recurrent
Networks.David Servan-Schreiber,
Axel Cleermans & James L.
McClelland
Chapter
XII: Extraction and Insertion of
Symbolic Information in Recurrent
Neural Networks. Christian W.
Omlin & C. L. Giles
Chapter
XIII: Logics and Variables in
Connectionist Models: A Brief
Overview. Ron Sun
Chapter
XIV: A Fault-Tolerant
Connectionist Architecture for
Construction of Logic Proofs.
Gadi Pinkas
Chapter
XV: Digital and Analog
Micro-circuit and Sub-net
Structures for Connectionist
Networks. Leonard Uhr
Chapter
XVI: Encoding Shape and Spatial
Relations: A Simple Mechanism for
Coordinating Complementary
Representations. Stephen M.
Kosslyn & Robert A. Jacobs
Chapter
XVII: Integrating Symbolic and
Neural Processing in a
Self-Organizing Architecture for
Pattern Recognition and
Prediction. Gail A. Carpenter
& Stephen Grossberg
Chapter
XVIII: Connectionist Grammars For
High-Level Vision. Eric Mjolsness
Chapter
XIX: Grounding Language in
Perception. Michael G. Dyer
Chapter
XX: Integrated Connectionist
Models: Building AI Systems on
Sub-symbolic Foundations. Risto
Miikkulainen
Chapter
XXI: Integrating Connectionist
and Symbolic Computation for the
Theory of Language. Paul
Smolensky, Geraldine Legendre
& Yoshiro Miyata
Chapter
XXII: Unified Learning Paradigm:
A Foundation for AI. Lev Goldfarb
& Sandeep Nigam
Chapter
XXIII: A Framework for Combining
Symbolic and Subsymbolic
Learning. Jude W. Shavlik
Chapter
XXIV: Learning and Representation
in Classifier Systems. Lashon B.
Booker, Rick L. Riolo & J. H.
Holland
Chapter
XXV: Toward Learning Systems That
Integrate Different Strategies
and Representations. Vasant
Honavar
Index