Abstract
This paper addresses the problem of minimizing an energy function by means of a monotonic transformation. With an observation on global optimality of functions under such a transformation, we show that a simple and effective algorithm can be derived to search within possible regions containing the global optima. Numerical experiments are performed to compare this algorithm with one that does not incorporate transformed information using several benchmark problems. These results are also compared to best known global search algorithms in the literature. In addition, the algorithm is shown to be useful for a class of neural network learning problems, which possess much larger parameter spaces.
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
Jacob Barhen, Vladimir Protopopescu, and David Reister. TRUST: A deterministic algorithm for global optimization. Science, 276:1094–1097, May 1997.
Djurdje Cvijović and Jacek Klinowski. Taboo search: An approach to the multiple minima problem. Science, 267:664–666, February 1995.
G. Cybenko. Approximations by superpositions of a sigmoidal function. Math. Cont. Signal & Systems, 2:303–314, 1989.
Ken-Ichi Funahashi. On the approximation realization of continuous mappings by neural networks. Neural Networks, 2:183–192, 1989.
Kurt Hornik, Maxwell Stinchcombe, and Halbert White. Multi-layer feedforward networks are universal approximators. Neural Networks, 2(5):359–366, 1989.
Reiner Horst and Panos M. Pardalos, editors. Handbook of Global Optimization. Kluwer Academics Publishers, 1995.
Reiner Horst and Hoang Tuy. Global Optimization: Deterministic Approaches. Springer-Verlag, Berlin, 1996.
Peter J. Huber. Projection pursuit. The Annals of Statistics, 13(2):435–475, 1985.
A.H.G Rinnooy Kan and G. T. Timmer. Stochastic global optimization methods part II: Multi level methods. Mathematical Programming, 39:57–78, 1987. (North-Holland).
Andrei Nikolaevich Kolmogorov. On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition. Doklalady Akademii Nauk SSSR, 114:953–956, 1957. (American Mathematical Society Translation, vol. 28, pp. 55–59, 1963).
Steve Lawrence, C. Lee Giles, Ah Chung Tsoi, and Andrew D. Back. Face recognition: A convolutional neural-network approach. IEEE Tran. Neural Networks, 8(1):98–113, 1997.
Kenneth Levenberg. A method for the solution of certain non-linear problems in least squares. Quarterly Journal of Applied Mathematics, 2:164–168, 1944.
David G. Luenberger. Linear and Nonlinear Programming. Addison-Wesley Publishing Company, Inc., Massachusetts, 1984.
Donald W. Marquardt. An algorithm for least-squares estimation of nonlinear parameters. Journal of the Society for Industrial & Applied Mathematics, 11(2):431–441, 1963.
H. L. Royden. Real Analysis. MacMillan Publishing Co., Inc., New York, 2 edition, 1988.
K. A. Toh, Juwei Lu, and Wei-Yun Yau. Global feedforward neural networks learning for classification and regression. In Proceedings of Third International Workshop on Energy Minimization Methods in Computer Vision and Pattern Recognition (EMMCVPR). Springer Verlag, Sophia-Antipolis, France, September 2001. (Lecture Notes in Computer Science).
Aimo Törn and Antanas Žilinskas. Global Optimization. Springer-Verlag, Berlin, 1989. (Lecture Notes in Computer Science).
Benjamin W. Wah and Yao-Jen Chang. Traced-based methods for solving nonlinear global optimization and satisfiability problems. J. Global Optimization, 10(2):107–141, 1997.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Toh, KA. (2001). Global Energy Minimization: A Transformation Approach. In: Figueiredo, M., Zerubia, J., Jain, A.K. (eds) Energy Minimization Methods in Computer Vision and Pattern Recognition. EMMCVPR 2001. Lecture Notes in Computer Science, vol 2134. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44745-8_26
Download citation
DOI: https://doi.org/10.1007/3-540-44745-8_26
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42523-6
Online ISBN: 978-3-540-44745-0
eBook Packages: Springer Book Archive