Density estimation with Genetic Programming for Inverse Problem solving

Abstract : This paper addresses the resolution, by Genetic Programming (GP) methods, of ambiguous inverse problems, where for a single input, many outputs can be expected. We propose two approaches to tackle this kind of many-to-one inversion problems, each of them based on the estimation, by a team of predictors, of a probability density of the expected outputs. In the first one, Stochastic Realisation GP, the predictors outputs are considered as the realisations of an unknown random variable which distribution should approach the expected one. The second one, Mixture Density GP, directly models the expected distribution by the mean of a Gaussian mixture model, for which genetic programming has to find the parameters. Encouraging results are obtained on four test problems of different difficulty, exhibiting the interests of such methods.
Type de document :
Communication dans un congrès
Marc Ebner and Michael O'Neill and Aniko Ekart and Leonardo Vanneschi and Anna Isabel Esparcia-Alcazar. EuroGP'07, the 10th European Conference on Genetic Programming, Apr 2007, Valencia, Spain. Springer, 4445, pp.45--54, 2007, Lecture Notes in Computer Science. 〈10.1007/978-3-540-71605-1_5〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00164762
Contributeur : Sébastien Verel <>
Soumis le : lundi 23 juillet 2007 - 16:26:35
Dernière modification le : mardi 30 mai 2017 - 01:17:14

Identifiants

Collections

INSU | UNICE | I3S | UPMC | LOV

Citation

Michael Defoin Platel, Sébastien Verel, Manuel Clergue, Malik Chami. Density estimation with Genetic Programming for Inverse Problem solving. Marc Ebner and Michael O'Neill and Aniko Ekart and Leonardo Vanneschi and Anna Isabel Esparcia-Alcazar. EuroGP'07, the 10th European Conference on Genetic Programming, Apr 2007, Valencia, Spain. Springer, 4445, pp.45--54, 2007, Lecture Notes in Computer Science. 〈10.1007/978-3-540-71605-1_5〉. 〈hal-00164762〉

Partager

Métriques

Consultations de la notice

168