Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Information
Offered By: Association for Computing Machinery (ACM) via YouTube
Course Description
Overview
Explore a 20-minute conference talk from the FAccT 2021 virtual event that delves into the challenges of evaluating fairness in machine learning models when faced with uncertain and incomplete information. Learn how researchers P. Awasthi, A. Beutel, M. Kleindessner, J. Morgenstern, and X. Wang address this critical issue in the field of AI ethics and fairness. Gain insights into novel approaches for assessing model fairness under constrained data scenarios and understand the implications for developing more equitable AI systems.
Syllabus
Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Information
Taught by
ACM FAccT Conference
Related Courses
The Laws of Digital Data, Content and Artificial Intelligence (AI)University of Law via FutureLearn Artificial Intelligence Privacy and Convenience
LearnQuest via Coursera AI Accountability Essential Training
LinkedIn Learning Artificial Intelligence: an Overview
Politecnico di Milano via Coursera Building Responsible AI - Best Practices Across the Product Development Lifecycle
Data Science Dojo via YouTube