no code implementations • ACL 2022 • Ryan Steed, Swetasudha Panda, Ari Kobren, Michael Wick
A few large, homogenous, pre-trained models undergird many machine learning systems — and often, these models contain harmful stereotypes learned from the internet.
1 code implementation • 28 Oct 2020 • Ryan Steed, Aylin Caliskan
Recent advances in machine learning leverage massive datasets of unlabeled images from the web to learn general-purpose image representations for tasks from image classification to face recognition.
1 code implementation • 5 May 2020 • Ryan Steed, Benjamin Williams
Machine learning systems impact many stakeholders and groups of users, often disparately.
1 code implementation • 13 Feb 2020 • Ryan Steed, Aylin Caliskan
We shed light on the ways in which appearance bias could be embedded in face processing technology and cast further doubt on the practice of predicting subjective traits based on appearances.