Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure

Uncovering and Mitigating Algorithmic Bias through Learned Latent Structure

Recent research has highlighted the vulnerabilities of modern machine learning based systems to bias, especially for segments of society that are under-represented in training data. In this work, we develop a novel, tunable algorithm for mitigating the hidden, and potentially unknown, biases within...

Full description

Bibliographic Details
Main Authors: Soleimany, Ava, Amini, Alexander A, Schwarting, Wilko, Bhatia, Sangeeta N, Rus, Daniela L
Other Authors: Harvard University--MIT Division of Health Sciences and Technology
Format: Article
Language:en_US
Published: AAAI/ACM 2019
Online Access:http://hdl.handle.net/1721.1/121101
https://orcid.org/0000-0002-9673-1267
https://orcid.org/0000-0002-1293-2097
https://orcid.org/0000-0001-5473-3566

Internet

http://hdl.handle.net/1721.1/121101
https://orcid.org/0000-0002-9673-1267
https://orcid.org/0000-0002-1293-2097
https://orcid.org/0000-0001-5473-3566

Similar Items