[en] The authors study the complexity and propose an algorithm for the problem of determining, given p vectors of {-1,1}^n, all linear combinations of them which are also in {-1,1}^n. Computational results are reported. This problem corresponds to the detection of spurious states in neural networks.
Disciplines :
Sciences informatiques Mathématiques
Auteur, co-auteur :
Crama, Yves ; Université de Liège - ULiège > HEC Liège : UER > Recherche opérationnelle et gestion de la production
Hansen, Pierre
Jaumard, Brigitte
Langue du document :
Anglais
Titre :
Detection of spurious states of neural networks
Date de publication/diffusion :
1991
Titre du périodique :
IEEE Transactions on Neural Networks
ISSN :
1045-9227
Maison d'édition :
Institute of Electrical and Electronics Engineers (IEEE), Piscataway, Etats-Unis - New Jersey
J. J. Hopfield, “Neural networks and physical systems with emergent collective computational abilities,” Proc. Nat. Acad. Sci. U.S., vol. 79, pp. 2554-2558, 1982.
L. Personnaz, I. Guyon, and G. Dreyfus, “Collective computational properties of neural networks: New learning mechanisms,” Phys. Rev. A, vol. 34, pp. 4217-4228, 1986.
I. Kanter and H. Sompolinsky, “Associative recall of memory without errors,” Phys. Rev. A, vol. 35, pp. 380-392, 1987.
A. M. Odlyzko, “On subspaces spanned by random selections of - 1 vectors,” J. Combinatorial Theory A, vol. 47, pp. 124-133, 1988.
G. L. Nemhauser and L. A. Wolsey, Integer and Combinatorial Optimization. New York: Wiley, 1988.
