nafyi.
Thèmes / Exact deletion method for influence testing

Point de vue reformulé

Gifford describes deleting training inputs and their influence

David Gifford describes the paper’s method as deleting training inputs and all their influence. He says it enables efficient, large-scale deletion and shows that the results do not change.

David Gifford·Publié

Derrière ce point de vue

Les traductions sont destinées à la lecture ; les extraits originaux restent la source evidence.

When AI art has no author: MIT study finds generated images often can't be traced to any training data | MIT CSAIL

Extrait original

This paper introduces the first method that is absolute. You're actually deleting the inputs and deleting all influences of the inputs.
Contexte

"They really could not absolutely show that deleting individual things did not change the output. This is the first exact method for doing large-scale deletion efficiently and showing that the results don't change."

Ouvrir l’original · Paragraph 5 — quotation 3 (s’ouvre dans un nouvel onglet)Voir la page source