Detail View

A critical examination of the key issues, underlying assumptions, and relevant suggestions related to the reconciliation and principled integration of artificial intelligence and neural networks into successful hybrid systems. A comprehensive introduction to the basics of symbol processing and connectionist networks, and their integration, gives readers the necessary background to understand each network system. Numerous examples of the integration of artificial intelligence and neural networks for a variety of specific applications, including vision and pattern recognition, illustrate the possibilities and actualities of the resultant hybrid systems. Annotation copyright Book News, Inc. Portland, Or.

Information Provided By: :

CONTENTS
Contributors = ix
Preface = xiii
Introduction = xvii
Ⅰ. SYMBOL PROCESSORS VERSUS CONNECTIONIST NETWORKS = 1
 Chapter Ⅰ. Horse of A Different Colour? = 3
 Chapter Ⅱ. Architecture of Intelligence : The Problems and Current Approaches to Solutions = 21
 Chapter Ⅲ. Schema Theory : Cooperative Computation for Brain Theory and Distributed AI = 51
 Chapter Ⅳ. The Role of Interdisciplinary Research Involving Neuroscience in the Development of Intelligent Systems = 75
 Chapter Ⅴ. Why the Difference between Connectionism and Anything Else Is More Than You Might Think but Less Than You Might Hope = 93
Ⅱ. REPRESENTATION AND INFERENCE = 105
 Chapter Ⅵ. Beyond Symbolic : Toward a Kama-Sutra of Compositionality = 107
 Chapter Ⅶ. How Might Connectionist Systems Represent Propositional Attitudes? = 127
 Chapter Ⅷ. Three Horns of the Representational Trilemma = 155
 Chapter Ⅸ. Learned Categorical Perception in Neural Nets : Implications for Symbol Grounding = 191
 Chapter Ⅹ. Image and Symbol : Continuous Computation and the Emaergence of the Discrete = 207
 Chapter xi. Graded State Machines : The Representation of Temporal Contingencies in Simple Recurrent Networks = 241
 Chapter xii Extraction and Insertion of Symbolic Information in Recurrent Neural Networks = 271
 Chapter XIII. Logics and Variables in Connectionist Medels: A Brief Overview = 301
 Chapter XIV. A Fault-Tolerant Connectionist Architecture for Construction of Logic Proofs = 321
 Chapter XV. Digital and Analog Microcircuit and Sub-Net Structures for Connectionist
 Networks = 341
Ⅲ. VISION = 371
 Chapter XVI. Encoding Shape and Spatial Relations : A Simple Mechanism for Coordinating Complimentary Representations = 373
 Chapter XVII. Integrating Sysbolic and Neural Processing in a Self-Organizing Architecture for Pattern Recognition and Prediction = 387
 Chapter XVIII. Connectionist Grammars for High-Level Vision = 423
Ⅳ. LANGUAGE = 453
 Chapter XIX. Grounding Language in Perception = 455
 Chapter XX. Integrated Connectionist Models : Building AI Systems on Subsymbolic Foundations = 483
 Chapter XXI. Integrating Connectionist and Symbolic Computation for the Theory of  Language =  509
Ⅴ. LEARNING = 531
 Chapter XXII. The Unified Learning Paradigm: A Foundation for AI = 533
 Chapter XXIII. A Framework for Combining Symbolic and Neural Learning = 561
 Chapter XXIV. Learning and Representation in Classifier Systems = 581
 Chapter XXV. Toward Learning Systems That Integrate Different Strategies and Representations = 615
Index = 645