A Neural Network for Shortest Path Computation
This paper presents a new neural network to solve the shortest path problem for internetwork routing. The proposed solution extends the traditional single-layer recurrent Hopfield architecture introducing a two-layer architecture that automatically guarantees an entire set of constraints held by any...
| Autor principal: | |
|---|---|
| Outros Autores: | , |
| Formato: | report |
| Idioma: | por |
| Publicado em: |
2009
|
| Assuntos: | |
| Texto completo: | http://hdl.handle.net/10451/14147 |
| País: | Portugal |
| Oai: | oai:repositorio.ul.pt:10451/14147 |
| Resumo: | This paper presents a new neural network to solve the shortest path problem for internetwork routing. The proposed solution extends the traditional single-layer recurrent Hopfield architecture introducing a two-layer architecture that automatically guarantees an entire set of constraints held by any valid solution to the shortest path problem. This new method addresses some of the limitations of previous solutions, in particular the lack of reliability in what concerns succeeded and valid convergence. Experimental results show that a clear improvement in well-succeeded convergence can be achieved. Additionally, computation performance is also improved at the expense of slightly worse results |
|---|