- 713 Downloads
This chapter discusses the principles and foundations behind scatter search and its application to the problem of training neural networks. Scatter search is an evolutionary method that has been successfully applied to a wide array of hard optimization problems. Scatter search constructs new trial solutions by combining so-called reference solutions and employing strategic designs that exploit context knowledge. In contrast to other evolutionary methods like genetic algorithms, scatter search is founded on the premise that systematic designs and methods for creating new solutions afford significant benefits beyond those derived from recourse to randomization. Our implementation goal is to create a combination of the five elements in the scatter search methodology that proves effective when searching for optimal weight values in a multilayer neural network. Through experimentation, we show that our instantiation of scatter search can compete with the best-known training algorithms in terms of training quality while keeping the computational effort at a reasonable level.
Key wordsMetaheuristics neural networks optimization
Unable to display preview. Download preview PDF.
- El-Fallahi, A., and Martí, R., 2003, Tabu and Scatter Search for Training Neural Networks, in: Computational Modeling and Problem Solving in the Networked World, H. K. Bhargava, and N. Ye, ed., Interfaces in Computer Science and Operations Research, pp. 79–96.Google Scholar
- Glover F., 1963, Parametric combinations of local job shop rules, ONR Research Memorandum. 117, GSIA, Carnegie Mellon University, Pittsburgh, PA.Google Scholar
- Glover, F., 1977, Heuristics for integer programming using surrogate constraints, Decision Sciences 8; 156–166.Google Scholar
- Glover, F., 1998, A template for scatter search and path relinking, in: Artificial Evolution, Lecture Notes in Computer Science 1363, J. K. Hao, E. Lutton, E. Ronald, M. Schoenauer, D. Snyers, eds., Springer, pp. 13–54.Google Scholar
- Glover, F., 2004, Parametric tabu search for mixed integer programming, Technical Report, University of Colorado at Boulder; http://spot.colorado.edu/~glover/Recentpapers.htinl.Google Scholar
- Laguna, M., and Martí, R., 2000, Neural network prediction in a system for optimizing simulations, HE Transaction 34(3): 273–282.Google Scholar
- Laguna, M., and Martí, R., 2003, Scatter Search — Methodology and Implementations in C, Kluwer Academic Publishers, Boston.Google Scholar
- Press, W. H., Teukolsky, S. A., Vetterling, W. T., and Flannery, B. P., 1992, Numerical Recipes: The Art of Scientific Computing, Cambridge University Press (www.nr.com).Google Scholar