Résumé / Abstract Journal-club_Doctorants

Séminaire Doctoral / Seminar PhD

« Never say never: on the relation between the random forest-based random forest and the random forest model »

Pierre Boldrini
Institut d'Astrophysique de Paris (Paris, France)

The recently proposed algorithm, called RANSAC, was a hybrid of Random Forests and Regular Forests. It was designed to solve an optimization problem and has been used in solving the optimization problem of the state of the art. The paper I'm going to present proposes a method of RANSAC based on the Random Forest-based Random Forest Model to solve a problem that is similar to the popular problem of the SATALE problem. We have experimented with several different Random Forest solutions and the method has proved to be very efficient compared to previous algorithms. On the other hand, we have found that RANSAC is more efficient than some other algorithms for solving the SATALE problem. We have also implemented the solution by using a regularizer and by using RANSAC.
vendredi 18 février 2022 - 16:00
Salle des séminaires Évry Schatzman, Institut d'Astrophysique
Page web du séminaire / Seminar's webpage