Speaker Details
Rosemary Ke
Research Scientist at Deepmind
Rosemary Ke Slides.pdf
Her research centers around developing novel machine learning algorithms that can generalize well to changing environments. In her research, she focus on two key ingredients: credit assignment and causal learning. These two ingredients flow into and reinforce each other: Appropriate credit assignment can help a model refine itself only at relevant causal variables, while a model that comprehends causality sufficiently well can reason about the connections between causal variables and the effect of intervening on them. Such an improved model can adapt quickly to interventions, thereby avoiding a huge class of errors that impede systematic generalization, particularly out of distribution.
Rosemary Ke's Webpage