Generalized neural networks for spectral analysis: Dynamics and Liapunov functions

Neural Networks

Volumn 17, Issue 2, 2004, Pages 233-245

  Vegas, José M ^a   Zufiria, Pedro J ^b  

^a UNIVERSIDAD COMPLUTENSE DE MADRID   (Spain)

^b Escuela Tecnica Superior de Ingenieros de Caminos Canales y Puertos   (Spain)

Author keywords

Global behavior; Hebbian networks; Homogeneous functions; Liapunov functions; Nonlinear dynamics; Principal component analysis; Stability

Indexed keywords

CORRELATION METHODS; NEURAL NETWORKS; NONLINEAR SYSTEMS; PRINCIPAL COMPONENT ANALYSIS; SPECTRUM ANALYSIS;

LIAPUNOV FUNCTIONS; LOCAL STABILITY ANALYSIS;

LEARNING SYSTEMS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; MATHEMATICAL ANALYSIS; MATHEMATICAL MODEL; PRINCIPAL COMPONENT ANALYSIS; PRIORITY JOURNAL; SPECTROSCOPY;

EID: 1242315607     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neunet.2003.05.001     Document Type: Article

References (27)

1. Amann H. Ordinary differential equations. 1990;Walter de Gruyter.
2. Amari S.-. Natural gradient learning for over- and under-complete bases in ICA. Neural Computation. 11:1999;1875-1883.
3. Auchmuty G. Unconstrained variational principles for eigenvalues of real symmetric matrices. SIAM Journal of Mathematical Analysis. 20:(5):1989;1186- 1207.
4. Bertsekas D. Nonlinear programming. 1996;Athena Scientific.
5. Berzal A., Zufiria P. J., (1998). Linearized Training of Hebbian Neural Networks: application in image processing, Engineering Benefits from Neural Networks, Systems Engineering Association, pp. 1-8, Gibraltar.
6. Berzal J. A., Zufiria P. J., Rodríguez L (1996). Implementing the Karhunen-Loeve transform via improved neural networks, Solving Engineering Problems with Neural Networks. International Conference on Engineering Applications of Neural Networks, EANN'96. pp. 375-378, London 1996.
7. Cohen M.A., Grossberg S. Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Transactions on Systems, Man and Cybernetics. 13:(5):1983;815-826.
8. Coll B., Gasull A., Prohens R. Differential Equations defined by the sum of two quasihomogeneous vector fields. Canadian Journal of Mathematics. 49:(2):1997;212-231.
9. Diamantaras K.I., Kung S.Y. Principal component neural networks. Theory and applications. 1996;Wiley, New York.
10. Edelman A., Arias T.A., Smith S.T. The geometry of algorithms with orthogonality constraints. SIAM Journal on Matrix Analysis Applications. 20:(2):1998;303-353.
11. Fiori S. A theory of learning by weight flow on Stiefel-Grassman Manifold. Neural Computation. 13:(7):2001;1625-1647.
12. Golub G.H., Van Loan C.H. Matrix computations. 1983;Johns Hopkins University Press, North Oxford Academic.
13. Haykin S. Neural Networks. A comprehensive foundation. 1994;Macmillan Publishing Company.
14. Helmke U., Moore J.B. Optimization and dynamical systems. 1996;Springer, London.
15. Hyvärinen A., Karhunen J., Oja E. Independent component analysis. 2001;Wiley, New York.
16. Johnson R.A., Wichern D.W. Applied multivariate statistical analysis. 1992;Prentice Hall, New Jersey.
17. Kushner H.J., Yin G.G. Stochastic approximation algorithms and applications. 1997;Springer, New York.
18. Ljung L. Analysis of recursive stochastic algorithms. IEEE Transactions on Automatic Control. AC-22:1977;551-575.
19. Oja E. A simplified neuron model as a principal component analyzer. Journal of Mathematical Biology. 15:1982;267-273.
20. Plumbley M.D. Lyapunov functions for convergence of principal component algorithms. Neural Networks. 8:(1):1995;11-23.
21. Samardzija N., Waterland R.L. A neural network for computing eigenvectors and eigenvalues. Biological Cybernetics. 65:1991;211-214.
22. Sanger T.D. Optimal unsupervised learning in a single-layer linear feedforward neural network. Neural Networks. 2:1989;459-473.
23. Yan W.-Y., Helmke U., Moore J.B. Global analysis of Oja's flow for neural networks. IEEE Transactions on Neural Networks. 5:(5):1994;674-683.
24. Tolmos P., Vegas J.M., Zufiria P.J. Estabilidad de sistemas dinámicos, asociados a redes neuronales, diseñados para el cálculo de autovectores de operadores lineales y no lineales. XVI CEDYA/VI Congreso de Matemática Aplicada. II:1999;. pp. 1619-1626.
25. Zhang Q., Bao Z. Dynamical system for computing the eigenvectors associated with the largest eigenvalue of a positive definite matrix. IEEE Transactions on Neural Networks. 6:(3):1995;790-791.
26. Zhang Q., Leung Y.-W. Energy function for one-unit Oja algorithm. IEEE Transactions on Neural Networks. 6:(5):1995;1291-1293.
27. Zufiria P.J. On the discrete-time dynamics of the basic Hebbian neural network node. IEEE Transactions on Neural Networks. 13:(6):2002;1342-1352.