Rede neural recorrente com perturbação simultânea aplicada no problema do caixeiro viajante / Recurrent neural network with simultaneous perturbation applied to traveling salesman problem
AUTOR(ES)
Fabriciu Alarcão Veiga Benini
DATA DE PUBLICAÇÃO
2008
RESUMO
This work proposes to solve the classic combinatorial optimization problem known as traveling salesman problem. A recurrent neural network was used in the system of optimization to search the shorter path. The structural topology linking the feedbacks of the network adopted here is known by Wang recurrent network. As learning rule to find the appropriate values of the weights was used the simultaneous perturbation with stochastic approximation. A detailed bibliographical revision on multivariable optimization with simultaneous perturbation is also described. Comparative results with other different techniques applied to the traveling salesman are still presented for validation purposes.
ASSUNTO(S)
combinatorial problem recurrent neural network rede recorrente de wang learning rule simultaneous perturbation stochastic approximation problema do caixeiro viajante traveling salesman problem perturbação simultânea com aproximação estocástica regra de treinamento problema combinatorial wang recurrent network rede neural recorrente
Documentos Relacionados
- O problema do caixeiro viajante com restrições de empacotamento tridimensional
- ALGORITMO EVOLUTIVO PARA O PROBLEMA DO CAIXEIRO VIAJANTE COM DEMANDAS HETEROGÊNEAS
- ESTRATÉGIAS PARALELAS INTELIGENTES PARA O MÉTODO BRANCH-AND-BOUND APLICADAS AO PROBLEMA DO CAIXEIRO VIAJANTE ASSIMÉTRICO
- Algoritmo memético com infecção viral: uma aplicação ao problema do caixeiro viajante assimétrico
- Aplications of genetic and fuzzy metaheusistic in the ant colony system for the traveling salesman problem