Explore the theory of algorithmic fairness and its implications in this 54-minute conference talk by Cynthia Dwork from Harvard University. Delve into fundamental questions raised by algorithmic fairness, focusing on the concept of "individual probability." Examine the proposed notion of Outcome Indistinguishability and its wide-ranging applications. Gain insights into the intersection of mathematics, deep learning, and trustworthy artificial intelligence. Learn about emerging directions in AI accountability, fairness, privacy, and safety. Understand how this research impacts academia, industry, policymaking, and society at large.
Overview
Syllabus
Algorithmic fairness and individual probabilities - Cynthia Dwork, Harvard University
Taught by
Alan Turing Institute
Related Courses
-
Cynthia Dwork - Group Fairness and Individual Fairness - IPAM at UCLA
-
Algorithmic Fairness, Loss Minimization and Outcome Indistinguishability
-
Algorithmic Fairness and Quantum Computation
-
Towards Safe, Reliable and Trustworthy AI
-
Implementing Intersectionality in Algorithmic Fairness - Keynote Panel I
-
Fairness and Robustness in Machine Learning – A Formal Methods Perspective - Aditya Nori, Microsoft
