Speaker

Rosemary Nan Ke

PhD Candidate

Montreal Institute of Learning Algorithms

About Rosemary Nan

Rosemary is a fourth-year PhD student at the Mila institute, advised by Yoshua Bengio and Chris Pal, she is also a Facebook fellow. Her primary research interests center around developing novel machine learning algorithms for causal learning and credit assignment.

A major challenge of contemporary deep learning is to generalize well outside the i.i.d. setting, when we care about generalization or fast adaptation to distributions different from the main training distribution. It has been argued that this requires learning not mere statistical associations between variables, but also the underlying causal model. Rosemary has been working on developing novel machine learning methods that merges contemporary deep learning and deep reinforcement learning with causal learning.

For links to papers, open-sourced codes and videos, please visit her website https://nke001.github.io.

Topic