BulDML at Institute of Mathematics and Informatics >
International Journal ITA >
2005 >
Volume 12 Number 2 >

Please use this identifier to cite or link to this item:

Title: A New Approach for Eliminating the Spurious States in Recurrent Neural Networks
Authors: Gimenez-Martinez, Victor
Torres, Carmen
Joaquin Erviti Anaut, Jose
Perez-Castellanos, Mercedes
Keywords: Learning Systems
Pattern Recognition
Graph Theory
Image Processing
Recurrent Neural Networks
Issue Date: 2005
Publisher: Institute of Information Theories and Applications FOI ITHEA
Abstract: As is well known, the Convergence Theorem for the Recurrent Neural Networks, is based in Lyapunov ́s second method, which states that associated to any one given net state, there always exist a real number, in other words an element of the one dimensional Euclidean Space R, in such a way that when the state of the net changes then its associated real number decreases. In this paper we will introduce the two dimensional Euclidean space R2, as the space associated to the net, and we will define a pair of real numbers ( x, y ) , associated to any one given state of the net. We will prove that when the net change its state, then the product x ⋅ y will decrease. All the states whose projection over the energy field are placed on the same hyperbolic surface, will be considered as points with the same energy level. On the other hand we will prove that if the states are classified attended to their distances to the zero vector, only one pattern in each one of the different classes may be at the same energy level. The retrieving procedure is analyzed trough the projection of the states on that plane. The geometrical properties of the synaptic matrix W may be used for classifying the n-dimensional state- vector space in n classes. A pattern to be recognized is seen as a point belonging to one of these classes, and depending on the class the pattern to be retrieved belongs, different weight parameters are used. 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.
ISSN: 1313-0463
Appears in Collections:Volume 12 Number 2

Files in This Item:

File Description SizeFormat
ijita12-2-p03.pdf131.84 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


Valid XHTML 1.0!   Creative Commons License