Learning block memories with metric networks
Entity
UAM. Departamento de Ingeniería InformáticaPublisher
World Academy of Science, Engineering and TechnologyDate
2008-01-20Citation
Proceedings of World Academy of Science, Engineering and Technology 2.1 (2008): 827-830ISSN
2010-376X (print); 2010-3778 (online)Funded by
This work was supported by TIN 2004-04363-CO03-03, TIN 2007-65989 and CAM S-SEM-0255-2006.Project
Comunidad de Madrid. S2006/SEM-0255/OLFACTOSENSEEditor's Version
http://waset.org/Publication/learning-block-memories-with-metric-networks/231Subjects
Hebbian learning; Image recognition; Small world; Spatial information; InformáticaRights
© 2008 World Academy of Science, Engineering and TechnologyAbstract
An attractor neural network on the small-world topology
is studied. A learning pattern is presented to the network, then
a stimulus carrying local information is applied to the neurons and
the retrieval of block-like structure is investigated. A synaptic noise
decreases the memory capability. The change of stability from local
to global attractors is shown to depend on the long-range character
of the network connectivity.
Files in this item
Google Scholar:González, Mario
-
Domínguez Carreta, David Renato
-
Rodríguez Ortiz, Francisco Borja
This item appears in the following Collection(s)
Related items
Showing items related by title, author, creator and subject.