AI Fairness 360 (AIF360) is a comprehensive open-source toolkit of metrics to check for unwanted bias in datasets and machine learning models, and state-of-the-art algorithms to mitigate such bias throughout the AI application lifecycle. Containing over 30 fairness metrics and 9 state-of-the-art bias mitigation algorithms developed by the research community, it is designed to translate algorithmic research from the lab into actual practice. Here’s IBM’s press release.
- Precedent in a Polarized Era
- CRS Report: The Legislative Process on the House Floor: An Introduction
- CRS Report: Abortion: Judicial History and Legislative Response
- Weekend Reading: Souza’s Shade: A Tale of Two Presidents
- Google’s Year in Search 2018
- Meet the 2018 I Love My Librarian Award Recipients
- Read Accused Russian Spy Maria Butina’s Plea Agreement
- Said & Silbey on Narrative Topoi in the Digital Age
- CRS Report: Shutdown of the Federal Government: Causes, Processes, and Effects
- Read AMI’s Non-Prosecution Agreement
Just in case you don't get it: The views expressed are solely those of the blog post author and should not be attributed to anyone else, meaning they do not necessarily represent the views of any organization that the post author is affiliated with or with the views of any other author who publishes on this blog.
- 185,636 hits