Recent works find that AI algorithms learn biases from data. Therefore, it is urgent and vital to identify biases in AI algorithms. However, previous bias identification methods overly rely on human experts to conjecture potential biases, which may neglect other underlying biases not realized by humans. Is there an automatic way to assist human experts in finding biases in a broad domain of image classifiers? In this talk, I will introduce solutions.
talk-data.com
C
Speaker
Chenliang Xu
2
talks
Associate Professor
University of Rochester
Associate Professor in the Department of Computer Science at the University of Rochester. His research originates in computer vision and tackles interdisciplinary topics, including video understanding, audio-visual learning, vision and language, and methods for trustworthy AI. He has authored over 90 peer-reviewed papers in computer vision, machine learning, multimedia, and AI venues.
Bio from: Feb 2024 – AI, Machine Learning & Data Science Meetup
Filter by Event / Source
Talks & appearances
2 activities · Newest first
Recent works find that AI algorithms learn biases from data. Therefore, it is urgent and vital to identify biases in AI algorithms. However, previous bias identification methods overly rely on human experts to conjecture potential biases, which may neglect other underlying biases not realized by humans. Is there an automatic way to assist human experts in finding biases in a broad domain of image classifiers? In this talk, I will introduce solutions.