Parallel Distributed Processing: Explorations in the Microstructure of Cognition : Psychological and Biological Models - Couverture rigide

Rumelhart, David E.; McClelland, James L.; The PDP Research Group

Couverture rigide

ISBN 10 : 0262132184 ISBN 13 : 9780262132183

Editeur : MIT Press, 1986

Synopsis

Book by McClelland James L Rumelhart David E

A propos du livre

Présentation de l'éditeur

What makes people smarter than computers? The work described in these two volumes suggests that the answer lies in the massively parallel architecture of the human mind. It is some of the most exciting work in cognitive science, unifying neural and cognitive processes in a highly computational framework, with links to artificial intelligence. Although thought and problem solving have a sequential character when viewed over a time frame of minutes or hours, the authors argue that each step in the sequence is the result of the simultaneous activity of a large number of simple computational elements, each influencing others and being influenced by them. Parallel Distributed Processing describes their work in developing a theoretical framework for describing this parallel distributed processing activity and in applying the framework to the development of models of aspects of perception, memory, language, and thought. Volume 2 applies to a number of specific issues in cognitive science and neuroscience. Some chapters describe models of aspects of perception, memory, language, and thought. Others discuss the relation between parallel distributed processing models and neurophysiology or describe models that are specifically addressed to neurophysiological data. The book concludes with an epilogue noting the strengths and weaknesses of the approach and directions for the future.

Présentation de l'éditeur

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. A Bradford Book.

Détails de l'édition

• Éditeur: MIT Press
• Date d'édition: 1986
• ISBN 10: 0262132184
• ISBN 13: 9780262132183
• Reliure: Relié
• Langue: anglais
• Nombre de pages: 550