Cover; Half Title; Title Page; Copyright Page; Table of Contents; Introduction to the Updated Edition; Introduction; A Comparison of Models; 1. Models of Information Processing in the Brain; 1.1. Introduction; 1.2. Systems of Simple Units With Modifiable Interconnections; 1.3. Systems of Simple Units With Fixed Interconnections; 1.4. Parallel Hardware and the Symbol Processing Paradigm; 1.5. Parallelism and Distribution in the Mammalian Nervous System; 1.6. Summary; 2. A Connectionist Model of Visual Memory; 2.1. Introduction; 2.2. The Model: Example and Discussion

2.3. Learning, Reorganizing, ForgettingAppendix: The Symbolic Neural Unit; 3. Holography, Associative Memory, and Inductive Generalization; 3.1. Introduction; 3.2. Holographic Models; 3.3. Nonholographic Models; 3.4. The Associative Net; 3.5. A Comparison of Correlographic and Matrix Models; 3.6. The Inductive Net; 3.7. Conclusion; 4. Storage and Processing of Information in Distributed Associative Memory Systems; 4.1. Introduction; 4.2. Associative Mappings in Distributed Memory Systems; 4.3. The Neural Implementation of Associative Memory

4.4. Information Processing in Distributed Associative Memory4.5. Discussion of Certain Problems Which Arise With Physical Memory Models; Summary; 5. Representing Implicit Knowledge; 5.1. Al, Psychology, and Neuroscience; 5.2. Implicit versus Explicit Knowledge; 5.3. A Parallel Model for Knowledge Representation; 5.4. Future Directions; 6. Implementing Semantic Networks in Parallel Hardware; 6.1. Introduction; 6.2. A Programmable Parallel Computer; 6.3. From Semantic Nets To State Vectors; 6.4. Context-Sensitive Associations and Higher-Level Units; 6.5. Property Inheritance

6.6. Two Types of Conceptual Structure6.7. Memory Search as a Constructive Process; 6.8. Learning; 6.9. Extensions of the Model; 6.10. Loading Assemblies With Patterns; 6.11. Summary; 7. Skeleton Filters in the Brain; 7.1. Looking at the Brain; 7.2. Listening to the Brain; 7.3. Simplifying the Brain; 7.4. Modeling Memory; 7.5. Theory and Practice; 8. Categorization and Selective Neurons; 8.1. Introduction; 8.2. Vector Models; 8.3. Abstraction and Categorization; 8.4. Feedback Models: What is a Macrofeature?; 8.5. A Numerical Experiment; 9. Notes on a Self-Organizing Machine; 9.1. Introduction

9.2. On the Nature of Environment9.3. Associative Learning and Recall; 9.4. A Second Form of Learning: Development of High-Order Features; 9.5. A Spatial Coding Module; 9.6. A Temporal Coding Module; 9.7. Integration; 10. Parallel-Processing Mechanisms and Processing of Organized Information in Human Memory; 10.1. A Model For Item Recognition; 10.2. Organized Memory: Process and Structure; 10.3. Conclusions; Author Index; Subject Index

This update of the 1981 classic on neural networks includes new commentaries by the authors that show how the original ideas are related to subsequent developments. As researchers continue to uncover ways of applying the complex information processing abilities of neural networks, they give these models an exciting future which may well involve revolutionary developments in understanding the brain and the mind -- developments that may allow researchers to build adaptive intelligent machines. The original chapters show where the ideas came from and the new commentaries show where they are going

Description based upon print version of record.