Abstract
An analysis of basin cells for an error surface of an multilayer perceptron is presented. Utilizing the topological structure of the basin cells, an escaping strategy is proposed to solve difficult local minima problems. A numerical example is given to illustrate the proposed method and is shown to have a potential to locate better local minima efficiently.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Barhen, J., Protopopescu, V., Reister, D.: TRUST: A Deterministic Algorithm for Global Optimization. Science 276, 1094–1097 (1997)
Battiti, R.: First-and Second-Order Methods for Learning: Between Steepest Descent and Newton’s Methods. Neural Computation 4, 141–166 (1992)
Chiang, H.-D., Fekih-Ahmed, L.: Quasi-stability Regions of Nonlinear Dynamical Systems: Theory. IEEE Trans. Circuits and Systems 41, 627–635 (1996)
Haykin, S.: Neural Networks: A Comprehensive Foundation. Prentice Hall, New York (1999)
Jongen, H.T., Jonker, P., Twilt, F.: Nonlinear Optimization in \(\Re^{\rm n}\). Peter Lang Verlag, Frankfurt (1995)
Lee, J.: Dynamic Gradient Approaches to Compute the Closest Unstable Equilibrium Point for Stability Region Estimate and Their Computational Limitations. IEEE Trans. on Automatic Control 48, 321–324 (2003)
Lee, J., Chiang, H.-D.: A Singular Fixed-point Homotopy Method to Locate the Closest Unstable Equilibrium Point for Transient Stability Region Estimate. IEEE Trans. on Circuits and Systems- Part II 51, 185–189 (2004)
Lee, J., Chiang, H.-D.: A Dynamical Trajectory-Based Methodology for Systematically Computing Multiple Optimal Solutions of General Nonlinear Programming Problems. IEEE Trans. on Automatic Control 49, 888–899 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Yoon, Y., Lee, J. (2005). Solving Hard Local Minima Problems Using Basin Cells for Multilayer Perceptron Training. In: Wang, J., Liao, X., Yi, Z. (eds) Advances in Neural Networks – ISNN 2005. ISNN 2005. Lecture Notes in Computer Science, vol 3496. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11427391_95
Download citation
DOI: https://doi.org/10.1007/11427391_95
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-25912-1
Online ISBN: 978-3-540-32065-4
eBook Packages: Computer ScienceComputer Science (R0)