Machine unlearning is a subfield of machine learning that aims to remove the influence of a specific set of training examples — the "forget set" — from a trained model, say Fabian Pedregosa and Eleni Triantafillou, research scientists at Google.
“Fully erasing the influence of the data requested to be deleted is challenging since, aside from simply deleting it from databases where it’s stored, it also requires erasing the influence of that data on other artifacts such as trained machine learning models,” they say.
The NeurIPS 2023 Machine Unlearning Challenge, therefore, considers a scenario in which a subset of training images “must be forgotten to protect the privacy or rights of the individuals concerned.” The competition is hosted on Kaggle, and the starting kit is available now.
Learn more at Google Research.
See also:
- 14 popular AI algorithms and their uses — InfoWorld
- Global Outlook for AI Jobs and Skills — FOSSlife
- Source code is the most common sensitive data shared to ChatGPT — SDxCentral
Looking for a job?
Sign up for job alerts and check out the latest listings at Open Source JobHub.
Comments