Reading Group: Trust and Transparency in Machine Learning Systems

Starting from Tuesday October 23, 2018, Madeleine Ransom and I will be organizing a bi-weekly reading group on issues of trust and transparency that arise from the application of machine learning systems in social contexts. The reading group will focus on three inter-related topics:

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

For more information see the reading group’s website.