Abstract
A theoretical investigation of the dynamics of continuous Hopfield networks, in a modified formulation proposed by Abe, is undertaken. The fixed points are classified according to whether they lie inside or they are vertices of the unit hypercube. It is proved that interior equilibria are saddle points. Besides, a procedure is sketched that determines the basins of attraction of stable vertices. The calculations are completed for the two-neuron network. These results contribute to a solid foundation for these systems, needed for the study of practical problems such as local minima or convergence speed.
This work has been partially supported by the Spanish Ministerio de Ciencia y Tecnología (MCYT), Project No. TIC2001-1758.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hopfield, J.: Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Natl. Acad. Sci. USA 81 (1984) 3088–3092
Samad, T., Harper, P.: High-order Hopfield and Tank optimization networks. Parallel Computing 16 (1990) 287–292
Joya, G., Atencia, M.A., Sandoval, F.: Hopfield neural networks for optimization: Study of the different dynamics. Neurocomputing 43 (2002) 219–237
Tank, D., Hopfield, J.: ‘Neural’ computation of decisions in optimization problems. Biological Cybernetics 52 (1985) 141–152
Vidyasagar, M.: Minimum-seeking properties of analog neural networks with multilinear objective functions. IEEE Trans. on Automatic Control 40 (1995) 1359–1375
Abe, S.: Theories on the Hopfield neural networks. In: Proc. IEE International Joint Conference on Neural Networks. Volume I. (1989) 557–564
Takefuji, Y., Lee, K.C.: Artificial neural networks for four-coloring map problems and k-colorability problems. IEEE Trans. On Circuits and Systems 38 (1991) 326–333
Abe, S.: Global convergence and suppresion of spurious states of the Hopfield neural networks. IEEE Trans. on Circuits and Systems-I 40 (1993) 246–257
Chen, T., Amari, S.I.: New theorems on global convergence of some dynamical systems. Neural Networks 14 (2001) 251–255
Tino, P., Horne, B., Giles, C.: Attractive periodic sets in discrete-time recurrent networks (with emphasis on fixed-point stability and bifurcations in two-neuron networks). Neural Computation 13 (2001) 1379–1414
Demmel, J.: Hermitian eigenproblems. In: Z. Bai, J. Demmel, J. Dongarra, A. Ruhe, H. van der Vorst, editors. Templates for the Solution of Algebraic Eigenvalue Problems: A Practical Guide, SIAM (2000)
Golub, G.H., van Loan, C.F.: Matrix computations. The Johns Hopkins University press (1996)
Guckenheimer, J., Holmes, P.: Nonlinear Oscillations, Dynamical Systems, and Bifurcations of Vector Fields. Springer Verlag (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Atencia, M., Joya, G., Sandoval, F. (2003). Spurious minima and basins of attraction in higher-order Hopfield networks. In: Mira, J., Álvarez, J.R. (eds) Computational Methods in Neural Modeling. IWANN 2003. Lecture Notes in Computer Science, vol 2686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44868-3_45
Download citation
DOI: https://doi.org/10.1007/3-540-44868-3_45
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40210-7
Online ISBN: 978-3-540-44868-6
eBook Packages: Springer Book Archive