The fundamental breakthroughs in machine learning, and the rapid advancements of the underlying deep neural network models have enabled the potential use of these systems in specialized, high stakes domains such as medicine. However, the increased capabilities of machine learning systems comes at the cost of greater complexity, with the design of machine learning systems becoming ever more laborious, computationally expensive and opaque. This can result in catastrophic failures and significantly hinders effective collaboration with human experts, which is central to successful deployment. In this talk, I overview steps towards an insight-driven design of machine learning systems, and methods to facilitate collaboration with human experts in medicine. I develop tools that enable the quantitative analysis of the complex hidden layers of deep neural networks, which provide both fundamental insights on central components of the models as well as informing algorithms for efficiently training these systems. I demonstrate how these trained systems can be adapted to work effectively with human experts in the medical setting, resulting in better outcomes than either entity alone.

Bio: Maithra Raghu recently finished her PhD at Cornell University, and is a senior research scientist at Google Brain. Her work centers on developing quantitative tools to gain insights into deep neural network representations, and using these insights to inform the design and training of ML systems, and how these systems can work effectively with human experts in specialized domains such as medicine.  Her work has been featured in many press outlets including The Washington Post, WIRED and Quanta Magazine. She has been named one of the Forbes 30 Under 30 in Science, a 2020 STAT Wunderkind, and a Rising Star in EECS.