- 771 Downloads
Simulated Annealing is a meta-heuristic that performs a randomized local search to reach near-optimal solutions of combinatorial as well as continuous optimization problems. In this chapter we show how it can be used to train artificial neural networks by examples. Experimental results indicate that good results can be obtained with little or no tuning.
Key wordsSimulated annealing neural networks
Unable to display preview. Download preview PDF.
- Aarts, E. H. L., and Korst, J. H. M., 1989, Simulated Annealing and Boltzmann Machines, Wiley.Google Scholar
- Binder, K., 1978, Monte Carlo Methods in Statistical Physics, Springer-Verlag.Google Scholar
- Glover, F., and Martí, R., 2006, Tabu search, Chapter 4 in this book.Google Scholar
- Feller, W., 1950, An Introduction to Probability Theory and Its Applications 1, Wiley.Google Scholar
- Isaacson, D., and Madsen, R., 1976, Markov Chains, Wiley.Google Scholar
- Lourenço, H. R., Martin, O., and Stützle, T., 2002, Iterated local search, in: Handbook of Metaheuristics, F. Glover and G. Kochenberger, eds., Kluwer A. P., 321–353.Google Scholar
- Seneta, E., 1981, Non-negative matrices and Markov chains, Springer-Verlag.Google Scholar