Approximating Viability Kernels With Support Vector Machines

Abstract : We propose an algorithm which performs a progressive approximation of a viability kernel, iteratively using a classification method. We establish the mathematical conditions that the classification method should fulfil to guarantee the convergence to the actual viability kernel. We study more particularly the use of support vector machines (SVMs) as classification techniques. We show that they make possible to use gradient optimisation techniques to find a viable control at each time step, and over several time steps. This allows us to avoid the exponential growth of the computing time with the dimension of the control space. It also provides simple and efficient control procedures. We illustrate the method with some examples inspired from ecology
Type de document :
Article dans une revue
IEEE Transactions on Automatic Control, Institute of Electrical and Electronics Engineers, 2007, 52 (5), pp.933 - 937. <10.1109/TAC.2007.895881>
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00616841
Contributeur : Laetitia Chapel <>
Soumis le : mercredi 24 août 2011 - 15:49:48
Dernière modification le : mercredi 24 août 2011 - 15:49:48

Identifiants

Collections

Citation

Guillaume Deffuant, Laetitia Chapel, Sophie Martin. Approximating Viability Kernels With Support Vector Machines. IEEE Transactions on Automatic Control, Institute of Electrical and Electronics Engineers, 2007, 52 (5), pp.933 - 937. <10.1109/TAC.2007.895881>. <hal-00616841>

Partager

Métriques

Consultations de la notice

112