THIERRY , Eric

International audience

We consider the situation where one wants to maximise a function f(theta,x) with respect to x, with theta unknown and estimated from observations y_k. This may correspond to the case of a regression model, where one observes y_k = f( theta,x_k) + epsilon _k, with epsilon_ k some random error, or to the Bernoulli case where y_k in {0,1}, with...

International audience

special issue on Valuetools selected papers

A design method is proposed that sequentially generates observation sites for the construction of a kriging predictive model. The objective of the construction is to allow a precise inversion of the system in the following sense: with any reachable target point T in the output space one wishes to be able to associate an input vector x_T such...

special issue on Valuetools selected papers

Nous proposons une méthode séquentielle pour maximiser la diversité des sorties d'un système pour lequel aucun modèle paramétrique n'est connu a priori. L'objectif est de pouvoir en quelque sorte "inverser le système", c'est-à-dire déterminer des valeurs d'entrée conduisant à des sorties proches de valeurs cibles quelconques. A chaque itération...

Signal averaging in equal-shape and equal-width signal classes is discussed. The aim is to compare two similarity criteria associated with the same clustering algorithm; one derived from the distribution function method and the other derived from correlation. The superiority of the fist one is proven first by simulation and then in the...