AI as statistical methods for imperfect theories - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

AI as statistical methods for imperfect theories

Résumé

Science has progressed by reasoning on what models could not predict because they were missing important ingredients. And yet without correct models, standard statistical methods for scientific evidence are not sound. Here, I argue that machine-learning methodology provides solutions to ground reasoning about empirically evidence more on models’ predictions, and less on their ingredients.
Fichier principal
Vignette du fichier
paper.pdf (103.17 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03474791 , version 1 (10-12-2021)
hal-03474791 , version 2 (13-12-2021)

Identifiants

  • HAL Id : hal-03474791 , version 2

Citer

Gaël Varoquaux. AI as statistical methods for imperfect theories. NeurIPS 2021 - 35th Conference on Neural Information Processing Systems. Workshop: AI for Science, Dec 2021, Virtual, France. ⟨hal-03474791v2⟩
765 Consultations
378 Téléchargements

Partager

Gmail Facebook X LinkedIn More