Title :
Neurogenetic approach for solving dynamic programming problems
Author :
Pires, Matheus Giovanni ; Da Silva, Ivan Nunes ; Bertoni, Fabiana Cristina
Author_Institution :
Dept. of Electr. Eng., Univ. of Sao Paulo, Sao Carlos
Abstract :
The shortest path problem is the classical combinatorial optimization problem arising in numerous planning and designing contexts. This paper presents a association of a modified Hopfield neural network, which is a computing model capable of solving a large class of optimization problems, with a genetic algorithm, that to make possible cover nonlinear and extensive search spaces, which guarantees the convergence of the system to the equilibrium points that represent solutions for the dynamic optimization problems. Experimental results are presented and discussed.
Keywords :
combinatorial mathematics; dynamic programming; genetic algorithms; search problems; combinatorial optimization problem; dynamic programming problems; genetic algorithm; modified Hopfield neural network; neurogenetic approach; search spaces; shortest path problem; Artificial neural networks; Constraint optimization; Design optimization; Dynamic programming; Equations; Genetic algorithms; Hopfield neural networks; Neurofeedback; Neurons; Shortest path problem; Hopfield neural network; genetic algorithm; shortest path problem;
Conference_Titel :
Systems, Man and Cybernetics, 2008. SMC 2008. IEEE International Conference on
Conference_Location :
Singapore
Print_ISBN :
978-1-4244-2383-5
Electronic_ISBN :
1062-922X
DOI :
10.1109/ICSMC.2008.4811609