MIOT : On AI hallucinations, no free lunches and the accuracy-stability trade-off in inverse problems

1 October 2024
from 13H30 to 14H30
  • EN
  • Accessible by videoconference
  • Public
  • Guillaume EYNARD-BONTEMPS Guillaume EYNARD-BONTEMPS Ingénieur Calcul Scientifique

Pour le 3ème séminaire scientifique "Mathématiques & Informatique pour l'observation de la Terre" de la COMET TSI, nous avons le plaisir de recevoir Nina Maria Gottschling, chercheuse au DLR, le mardi 1er octobre de 13h30 à 14h30 en visioconférence. 

 

Titre : On AI hallucinations, no free lunches and the accuracy-stability trade-off in inverse problems

Abstract : Methods inspired by Artificial Intelligence (AI) are starting to fundamentally change computational science and engineering through breakthrough performances on challenging problems. However, reliability and trustworthiness of such techniques is becoming a major concern. In inverse problems in imaging, the focus of this talk, there is increasing empirical evidence that methods may suffer from hallucinations, i.e., false, but realistic-looking artifacts; instability, i.e., sensitivity to perturbations in the data; and unpredictable generalization, i.e., excellent performance on some images, but significant deterioration on others. This talk presents a potential mathematical framework describing how and when such effects arise in arbitrary reconstruction methods, not just AI-inspired techniques. Several of our results take the form of `no free lunch' theorems. Our results trace these effects to the kernel of the forward operator whenever it is nontrivial, but also extend to the case when the forward operator is ill-conditioned. Lastly, an outlook onto the relevance and utility of these findings in Earth Observation is presented.

 

Lien d'accès web et applications :

Lien principal: https://rendez-vous.renater.fr/COMETTSIMIOT_305113-6f539a-92b59e

Share :

Partage possible par tous (via Facebook, LinkedIn, Twitter, email)

You may find these events interesting, as well