Connectionist symbol processing / edited by G.E. Hinton.
Contributor(s): Hinton, Geoffrey E
| IEEE Xplore (Online Service) [distributor.] | MIT Press [publisher.].
Material type: 
BookSeries: Special issues of <i>artificial intelligence</i>: Publisher: Cambridge, Massachusetts : MIT Press, 1991Distributor: [Piscataqay, New Jersey] : IEEE Xplore, [1991]Edition: 1st MIT Press ed.Description: 1 PDF (262 pages) : illustrations.Content type: text Media type: electronic Carrier type: online resourceISBN: 9780262256360.Subject(s): Connection machines | Neural networks (Computer science)Genre/Form: Electronic books.Additional physical formats: Print version: No titleDDC classification: 006.3 Online resources: Abstract with links to resource Also available in print.Summary: The six contributions in Connectionist Symbol Processing address the current tension within the artificial intelligence community between advocates of powerful symbolic representations that lack efficient learning procedures and advocates of relatively simple learning procedures that lack the ability to represent complex structures effectively. The authors seek to extend the representational power of connectionist networks without abandoning the automatic learning that makes these networks interesting.Aware of the huge gap that needs to be bridged, the authors intend their contributions to be viewed as exploratory steps in the direction of greater representational power for neural networks. If successful, this research could make it possible to combine robust general purpose learning procedures and inherent representations of artificial intelligence -- a synthesis that could lead to new insights into both representation and learning.
"A Bradford book."
"Reprinted from Artificial intelligence, an international journal, volume 46, numbers 1-2, 1990"--T.p. verso.
Includes bibliographical references and index.
Restricted to subscribers or individual electronic text purchasers.
The six contributions in Connectionist Symbol Processing address the current tension within the artificial intelligence community between advocates of powerful symbolic representations that lack efficient learning procedures and advocates of relatively simple learning procedures that lack the ability to represent complex structures effectively. The authors seek to extend the representational power of connectionist networks without abandoning the automatic learning that makes these networks interesting.Aware of the huge gap that needs to be bridged, the authors intend their contributions to be viewed as exploratory steps in the direction of greater representational power for neural networks. If successful, this research could make it possible to combine robust general purpose learning procedures and inherent representations of artificial intelligence -- a synthesis that could lead to new insights into both representation and learning.
Also available in print.
Mode of access: World Wide Web
Description based on PDF viewed 12/23/2015.
There are no comments for this item.