A Neural Network for Shortest Path Computation
Filipe Araújo, Bernardete Ribeiro and Luís Rodrigues
In IEEE Transaction on Neural Networks, Vol. 12,
N. 5, pp. 1067-1073, Sep. 2001.
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
successful and valid convergence. Experimental results show that an
improvement in successful convergence can be achieved in certain
classes of graphs. Additionally, computation performance is also
improved at the expense of slightly worse results.