2020-10-31T19:31:02Z
http://oa.upm.es/cgi/oai2
oai:oa.upm.es:2826
2016-04-20T12:28:33Z
7374617475733D707562
7375626A656374733D6D6174656D617469636173
7375626A656374733D696E666F726D6174696361
747970653D61727469636C65
A Statistical Convergence Application for the Hopfield Networks
Gimenez Martinez, Victor
Sanchez Torrubia, Maria Gloria
Torres Blanc, Carmen
Mathematics
Computer Science
When Recurrent Neural Networks (RNN) are going to be used as Pattern Recognition systems, the problem to be considered is how to impose prescribed prototype vectors ctors ξ 1 ,ξ 2 , ...,ξ p , as fixed points. The synaptic matrix W should be interpreted as a sort of sign correlation matrix of the prototypes, In the classical approach. The weak point in this approach, comes from the fact that it does not have the appropriate tools to deal efficiently with the correlation between the state vectors and the prototype vectors The capacity of the net is very poor because one can only know if one given vector is adequately correlated with the prototypes or not and we are not able to know what its exact correlation degree. The interest of our approach lies precisely in the fact that it provides these tools. In this paper, a geometrical vision of the dynamic of states is explained. A fixed point is viewed as a point in the Euclidean plane R2. The retrieving procedure is analyzed trough statistical frequency distribution of the prototypes. The capacity of the net is improved and the spurious states are reduced. In order to clarify and corroborate the theoretical results, together with the formal theory, an application is presented.
Facultad de Informática (UPM)
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
2008
info:eu-repo/semantics/article
Article
Information Theory and Applications, ISSN 1310-0513, 2008, Vol. 15, No. 1
PeerReviewed
application/pdf
spa
http://www.foibg.com/ijita/vol15/ijita-fv15.htm
info:eu-repo/semantics/openAccess
http://oa.upm.es/2826/