Statut | Confirmé |
Série | FORUM-ENS |
Domaines | cond-mat.stat-mech |
Date | Mercredi 6 Avril 2022 |
Heure | 15:00 |
Institut | LPENS |
Salle | Salle Djebar (29 rue d'Ulm) |
Nom de l'orateur | D'ascoli |
Prenom de l'orateur | Stéphane |
Addresse email de l'orateur | |
Institution de l'orateur | LPENS |
Titre | Tackling symbolic regression with Transformers |
Résumé | Symbolic regression, the task of predicting the mathematical expression of a function from the observation of its values, is a difficult task which has until now mainly been tackled with genetic algorithms. The latter involve costly searches through vast function spaces, and do not leverage past experience: each new problem is recomputed from scratch. In the first part of this talk, I will present our recent attempt at solving this problem via machine learning, by training Transformer models (originally built for machine translation) on huge datasets of synthetic examples. In the second part, I will present a specific application: that of recurrence prediction, i.e. recognising the recurrence relation of number sequences, for example 1,2,3,5,8->x_n=x_n-1 + x_n-2. |
Numéro de preprint arXiv | |
Commentaires | |
Fichiers attachés |
Pour obtenir l' affiche de ce séminaire : [ Postscript | PDF ]
|
[ English version ] |