Learning with monotonicity requirements for optimal routing with end-to-end quality of service constraints

Antoine Mahul (1) , Alexandre Aussem (2)

1 LIMOS - Laboratoire d'Informatique, de Modélisation et d'optimisation des Systèmes
2 LIESP - Laboratoire d'Informatique pour l'Entreprise et les Systèmes de Production

In this paper, we adapt the classical learning algorithm for feed-forward neural networks when monotonicity is required in the input output mapping. Monotonicity can be imposed by adding of suitable penalization terms to the error function. This yields a computationally efficient algorithm with little overhead compared to back-propagation. This algorithm is used to train neural networks for delay evaluation in an optimization scheme for optimal routing in a communication network.

Domaines: Réseau de neurones [cs.NE]; Autres [stat.ML]

Antoine Mahul, Alexandre Aussem. Learning with monotonicity requirements for optimal routing with end-to-end quality of service constraints. European Symposium on Artificial Neural Networks, ESANN'06, 2006, Bruges, Belgium. pp. ?. ⟨hal-00266057⟩