This event is organized by the Schwartz Reisman Institute for Technology and Society.
Our weekly SRI Seminar Series welcomes Rahul G. Krishnan, assistant professor in the Department of Computer Science and Department of Laboratory Medicine and Pathobiology at the University of Toronto. Krishnan is a Tier II Canada Research Chair in Computational Medicine, a Canada CIFAR AI Chair at the Vector Institute, and a faculty affiliate at the Schwartz Reisman Institute for Technology and Society.
Krishnan’s research is focused on developing machine learning algorithms to create a learning healthcare system, where digitized clinical and biological data are used to improve clinical care while improving our understanding of human and disease biology. His interests lie in deep learning, causal inference, generative and multi-modal models, and reliable machine learning.
Moderator: Ishtiaque Ahmed
Location: Online
Talk title:
“From associational to causal predictions with deep learning”
Abstract:
Over the last decade, we’ve made leaps and strides in our ability to leverage neural networks to solve increasingly general problems. Yet, the mechanisms by which neural networks make predictions are largely associational. In contrast, humans regularly reason causally when making predictions. This talk will highlight recent advances in bridging the gap between the two fields and motivate the rationale for studying, building, and scaling neural networks that reason causally.
Suggested readings:
Asic Q. Chen, Ruian Shi, Xiang Gao, Ricardo Baptista, Rahul G. Krishnan, “Structured Neural Networks for Density Estimation and Causal Inference,” arXiv, 2023.
Vahid Balazadeh, Keertana Chidambaram, Viet Nguyen, Rahul G. Krishnan, Vasilis Syrgkanis, “Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity,” arXiv, 2024.
Nikita Dhawan, Leonardo Cotta, Karen Ullrich, Rahul G. Krishnan, Chris J. Maddison, “End-To-End Causal Effect Estimation from Unstructured Natural Language Data,” arXiv, 2024.
About Rahul G. Krishnan
Rahul G. Krishnan is an assistant professor in the University of Toronto’s Department of Computer Science and Department of Laboratory Medicine and Pathobiology, where he holds a Tier II Canada Research Chair in Computational Medicine. Krishnan is also a CIFAR AI Chair at the Vector Institute, a member of the Temerty Center for Artificial Intelligence in Medicine (T-CAIREM), and a faculty affiliate at the Schwartz Reisman Institute for Technology and Society.
Krishnan’s research is focused on developing machine learning methods to automate clinical decision-making, including deep generative modeling, multi-modal models, and techniques for identifying interventional policies from time-varying observational data in healthcare. He previously worked as a senior researcher at Microsoft Research. Krishnan earned his Masters from New York University, and his PhD in electrical engineering and computer science from MIT in 2020.
About the SRI Seminar Series
The SRI Seminar Series brings together the Schwartz Reisman community and beyond for a robust exchange of ideas that advance scholarship at the intersection of technology and society. Seminars are led by a leading or emerging scholar and feature extensive discussion.
Each week, a featured speaker will present for 45 minutes, followed by an open discussion. Registered attendees will be emailed a Zoom link before the event begins. The event will be recorded and posted online.
Note: Event details can change. Please visit the unit’s website for the latest information about this event.