- 783 Downloads
Tabu Search is a metaheuristic that guides a local heuristic search procedure to explore the solution space beyond local optimality. One of the main components of tabu search is its use of adaptive memory, which creates a more flexible search behavior. Memory based strategies are therefore the hallmark of tabu search approaches, founded on a quest for “integrating principles,” by which alternative forms of memory are appropriately combined with effective strategies for exploiting them. In this chapter we address the problem of training multilayer feed-forward neural networks. These networks have been widely used for both prediction and classification in many different areas. Although the most popular method for training these networks is backpropagation, other optimization methods such as tabu search have been applied to solve this problem. This chapter describes two training algorithms based on the tabu search. The experimentation shows that the procedures provide high quality solutions to the training problem, and in addition consume a reasonable computational effort.
Key wordsIntelligent problem solving memory structures adaptive memory programming
Unable to display preview. Download preview PDF.
- Bishop, C. M., 1995, Neural Networks for Pattern Recognition, Oxford University Press.Google Scholar
- El-Fallahi A., 2002, Entrenamiento de Redes Neuronales, Trabajo de Investigatión, Dpto Estadśtica e I.O. University of Valencia.Google Scholar
- Fahlman, S. E., 1988, An empirical study of learning speed in back-propagation networks, in: Connectionist Models Summer School, T. J. Sejnowski, G. E. Hinton and D. S. Touretzky, eds., San Mateo, CA, Morgan Kaufmann, pp. 38–51.Google Scholar
- Glover, F., and Laguna, M., 1993, Tabu search, in: Modern Heuristic Techniques for Combinatorial Problems, C. Reeves, ed., Blackwell Scientific Publishing, Oxford, pp. 70–150.Google Scholar
- Laguna, M., Martí, R., 2003, Scatter Search—Methodology and Implementations in C, Kluwer Academic Publishers, Boston.Google Scholar
- Riedmiller, M., and Heinrich, B., 1993, A direct adaptive method for faster back-propagation learning: the RPROP algorithm, IEEE Intl. Conf. on Neural Networks, pp. 586–591.Google Scholar
- Rumelhart, D. E., and McClelland, J. L., 1986, Parallel distributed processing: explorations in the microstructure of cognition, Cambridge, MA: The MIT Press.Google Scholar