Reducing discrimination in classification algorithms

Discrimination and segregation have become major societal concerns while the increasing use of algorithms in various domains raises interest in their fairness and transparency. In this context, Flore will present why discriminations (based on gender, ethnicity, or other sensitive variables) may appear in the results produced by algorithms and how to reduce those biases. More precisely, she will detail her current work on a new approach to improve fairness (i.e. reduce discrimination) in supervised classification.
Please register by 11 December 2023