Production year
2021
© Christian MOREL / LIPN / CNRS Images
20230062_0040
Parmi les approches d’apprentissage non supervisé, le clustering et les cartes auto-organisées (SOM) fournissent des informations utiles sur la distribution de jeux de données non étiquetés complexes. Un modèle SOM profond original (Deep Embedded SOM), basé sur des réseaux de neurones combinant l’apprentissage de représentations via un auto-encodeur et l’auto-organisation des prototypes, a été développé.
The use of media visible on the CNRS Images Platform can be granted on request. Any reproduction or representation is forbidden without prior authorization from CNRS Images (except for resources under Creative Commons license).
No modification of an image may be made without the prior consent of CNRS Images.
No use of an image for advertising purposes or distribution to a third party may be made without the prior agreement of CNRS Images.
For more information, please consult our general conditions
2021
Our work is guided by the way scientists question the world around them and we translate their research into images to help people to understand the world better and to awaken their curiosity and wonderment.