Trust and Transparency in Machine Learning Systems

This a bi-weekly reading group at the The W. Maurice Young Centre for Applied Ethics. We discuss issues of trust and transparency that arise from the application of machine learning systems in social contexts. The group primary focuses on three topics:

• Senses and sources of algorithmic bias
• Methods for quantifying and mitigating algorithmic unfairness
• Methods for making machine learning models post-hoc interpretable

The format consists of paper-reading sessions that start with a mini-tutorial.

Time: Tuesdays, 12:45-2PM * Note that for the Spring 2019 semester we will be meeting only for people to present works in progress, see schedule for details*

Location: Room 225, Centre for Applied Ethics (Leonard S. Klinck building)

Reading Schedule: See the schedule page

Organizers: Madeleine Ransom and Sina Fazelpour

Contact: If you are interested in joining the group please contact Madeleine a madeleineransom [at] gmail [dot] com.