HEAL DSpace

Multi-network architecture for high generalization in pattern recognition with back-propagation neural network modules

DSpace/Manakin Repository

Show simple item record

dc.contributor.author Tzafestas, SG en
dc.contributor.author Anthopoulos, Y en
dc.date.accessioned 2014-03-01T02:41:09Z
dc.date.available 2014-03-01T02:41:09Z
dc.date.issued 1996 en
dc.identifier.issn 08843627 en
dc.identifier.uri https://dspace.lib.ntua.gr/xmlui/handle/123456789/30394
dc.subject backpropagation en
dc.subject backpropagation neural network en
dc.subject Function Approximation en
dc.subject Network Architecture en
dc.subject Networked Learning en
dc.subject Pattern Classification en
dc.subject Pattern Recognition en
dc.subject.other Algorithms en
dc.subject.other Approximation theory en
dc.subject.other Backpropagation en
dc.subject.other Computer architecture en
dc.subject.other Image analysis en
dc.subject.other Learning systems en
dc.subject.other Mathematical models en
dc.subject.other Neural networks en
dc.subject.other Random processes en
dc.subject.other Multinetwork architecture en
dc.subject.other Pattern recognition en
dc.title Multi-network architecture for high generalization in pattern recognition with back-propagation neural network modules en
heal.type conferenceItem en
heal.identifier.primary 10.1109/ICSMC.1996.569887 en
heal.identifier.secondary http://dx.doi.org/10.1109/ICSMC.1996.569887 en
heal.publicationDate 1996 en
heal.abstract Back-propagation networks are the most popular multi-layer networks, used for either function approximation or pattern classification. They are trained and tested using two disjoint sets of patterns drawn randomly from the pattern space. In many cases, the overtraining phenomenon occurs i.e. the network learns to produce the proper output for the patterns to which it has been trained but it produces meaningless outputs for unforeseen patterns. In this paper, the overtraining phenomenon is analyzed in depth, and an alternative architecture with increased generalization ability is proposed. en
heal.publisher IEEE, Piscataway, NJ, United States en
heal.journalName Proceedings of the IEEE International Conference on Systems, Man and Cybernetics en
dc.identifier.doi 10.1109/ICSMC.1996.569887 en
dc.identifier.volume 1 en
dc.identifier.spage 741 en
dc.identifier.epage 746 en


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record