Serge Dégerine

Learn More
— This paper deals with the problem of blind separation of an instantaneous mixture of Gaussian autore-gressive sources, without additive noise, by the exact maximum likelihood approach. The maximization of the likelihood function is divided, using relaxation, into two sub-optimization problems, still solved by relaxation methods. The first one consists in(More)
— A comparative study of approximate joint diago-nalization algorithms of a set of matrices is presented. Using a weighted least-squares criterion, without the orthogonality constraint, an algorithm is compared with an analoguous one for blind source separation (BSS). The criterion of the present algorithm is on the separating matrix while the other is on(More)
This paper presents the problem of maximizing the determinant of a K-square real matrix B, subject to the constraint that each row b k of B satisfies b t k Γ k b k ≤ 1, where Γ 1 ,. .. , Γ K , are K given real symmetric positive definite matrices. Existence and uniqueness of the solution is discussed. An iterative algorithm, using a method of relaxation(More)