Explore cutting-edge research on fairness methods in machine learning and artificial intelligence in this 44-minute conference session from the ACM FAT* 2019 conference. Chaired by Zack Lipton, the session features three presentations on innovative approaches to addressing bias and fairness in AI systems. Learn about causal latent-variable models for handling biased data, the challenges of translating soft classifiers into fair hard decisions, and the potential of deep weighted averaging classifiers. Gain insights into the latest techniques for promoting fairness and mitigating bias in AI applications from leading researchers in the field.
Overview
Syllabus
FAT* 2019: Fairness Methods
Taught by
ACM FAccT Conference
Related Courses
-
Fairness in Machine Learning - Lessons from Political Philosophy
-
Challenges of Incorporating Algorithmic Fairness into Industry Practice
-
Translation Tutorial - Engineering for Fairness - How a Firm Conceptual Distinction between Unfairness and Bias Makes it Easier to Address Un-Fairness
-
Law and Policy
