MIT CogNet, The Brain Sciences ConnectionFrom the MIT Press, Link to Online Catalog
SPARC Communities
Subscriber : Stanford University Libraries » LOG IN

space

Powered By Google 
Advanced Search

Selected Title Details  
Jul 1987
ISBN 0262631105
632 pp.
BUY THE BOOK
Parallel Distributed Processing - Vol. 2
James L. McClelland and David E. Rumelhart

"The ideas represented in Parallel Distributed Processing fundamentally challenge the main concepts and assumptions of modern cognitive science."
- James G. Greeno, The New York Times Book Review

What makes people smarter than computers? These volumes by a pioneering neurocomputing group suggest that the answer lies in the massively parallel architecture of the human mind. They describe a new theory of cognition called connectionism that is challenging the idea of symbolic computation that has traditionally been at the center of debate in theoretical discussions about the mind.

The authors' theory assumes the mind is composed of a great number of elementary units connected in a neural network. Mental processes are interactions between these units which excite and inhibit each other in parallel rather than sequential operations. In this context, knowledge can no longer be thought of as stored in localized structures; instead, it consists of the connections between pairs of units that are distributed throughout the network.

Volume 1 lays the foundations of this exciting theory of parallel distributed processing, while Volume 2 applies it to a number of specific issues in cognitive science and neuroscience, with chapters describing models of aspects of perception, memory, language, and thought.

"Rumelhart and McClelland propose that what is stored in memory is not specific facts or events, but rather the relationships between the various aspects of those facts or events as they are encoded in groupings of neuronal cells or patterns of cell activity."
- Daniel Coleman, The New York Times

"The most intense, most effective and most mind-stretching view of neurocomputing origins, theories and concerns to yet reach print."
- Intelligence

"[This is] a comprehensive compilation of neural network research and development. There are algorithms you can use to explore various methods in the field. If you want information on neural network technology in book form, this is the set to own."
- Artificial Intelligence Special Interest Group Newsletter

David E. Rumelhart is Professor of Psychology at the University of California, San Diego. James L. McClelland is Professor of Psychology at Carnegie-Mellon University.

Table of Contents
 Preface to Volume 2
 Addresses of the PDP Research Group
IV PSYCHOLOGICAL PROCESSES
14 Schemata and Sequential Thought Processes in PDP Models
by D. E. Rumelhart, P. Smolensky, J. L. McClelland and G. E. Hinton
15 Interactive Processes in Speech Perception: The TRACE Model
by J. L. McClelland and J. L. Elman
16 The Programmable Blackboard Model of Reading
by J. L. McClelland
17 A Distributed Model of Human Learning and Memory
by J. L. McClelland and D. E. Rumelhart
18 On Learning the Past Tenses of English Verbs
by D. E. Rumelhart and J. L. McClelland
19 Mechanisms of Sentence Processing: Assigning Roles to Constituents
by J. L. McClelland and A. H. Kawamoto
V BIOLOGICAL MECHANISMS
20 Certain Aspects of the Anatomy and Physiology of the Cerebral Cortex
by F. H. C. Crick and C. Asanuma
21 Open Questions About Computation in Cerebral Cortex
by T. J. Sejnowski
22 Neural and Conceptual Interpretation of PDP Models
by P. Smolensky
23 Biologically Plausible Models of Place Recognition and Goal Location
by D. Zipser
24 State-Dependent Factors Influencing Neural Plasticity: A Partial Account of the Critical Period
by P. W. Munro
25 Amnesia and Distributed Memory
by J. L. McClelland and D. E. Rumelhart
VI CONCLUSION
26 Reflections on Cognition and Parallel Distributed Processing
by D. A. Norman
 Future Directions
 References
 Index
 
Options
Related Topics
Computational Intelligence
Neuroscience
Psychology, Cognitive Science


© 2010 The MIT Press
MIT Logo