Afaf Taik is currently a Claire DesChênes Postdoctoral Fellow at Mila- Quebec AI Institute and Université de Montréal, working on the intersection of fairness and privacy in machine learning with Dr. Golnoosh Farnadi. She has obtained a PhD in Electrical engineering in June 2022 from Université de Sherbrooke, where she worked under the supervision of Pr. Soumaya Cherkaoui on problems related to distributed machine learning algorithms in wireless networks. Before that, she has obtained a DESS from Université de Sherbrooke (2018), and a software engineering degree from ENSIAS, Morocco (2018). During her PhD, she has received the Leonard De Vinci medal from the engineering faculty at Université de Sherbrooke, and the best paper award at IEEE LCN 2021.
SESSION
THIS PRESENTATION WILL BE HELD IN ENGLISH
Towards Inclusive AI: Understanding Bias in Machine Learning Models
Machine learning models encode many biases and amplify them, leading to various societal harms. In this talk, we discuss how biases propagate through the machine-learning pipeline and lead to harm. We also highlight existing mitigation efforts with a focus on large language models.