Yale Institute for Foundations of Data Science, Kline Tower 13th Floor, Room 1327, New Haven, CT 06511
Speaker: Shirley Ho, Group Leader (Cosmology & Machine Learning), Center for Computational Astrophysics, Flatiron Institute, Simons Foundation
Research Professor of Physics & Affiliate Faculty at Center for Data Science, New York University
Wednesday, November 15, 2023
Tea & Reception: 3:30 pm (Kitchen)
Talk: 4:00 pm (Room #1327)
at the Yale institute for Foundations of Data Science, Kline Tower, 13th Floor
“Foundation Models for Science”
Abstract: In recent years, the fields of natural language processing and computer vision have been revolutionized by the success of large models pretrained with task-agnostic objectives on massive, diverse datasets. This has, in part, been driven by the use of self-supervised pretraining methods which allow models to utilize far more training data than would be accessible with supervised training. These so-called “foundation models″ have enabled transfer learning on entirely new scales. Despite their task-agnostic pretraining, the features they extract have been leveraged as a basis for task-specific finetuning, outperforming supervised training alone across numerous problems especially for transfer to settings that are insufficiently data-rich to train large models from scratch. In this talk, I will show our preliminary results on applying this approach to a variety of scientific problems and speculate what are possible future directions.
Speaker Bio: Shirley Ho is an American astrophysicist and machine learning expert, currently at the Center for Computational Astrophysics at Flatiron Institute in NYC and at New York University, with visiting appointment at Princeton University.
A cited expert in cosmology, machine learning applications in science, and data science, her interests include developing and deploying deep learning techniques to better understand our Universe and other physical phenomena.
Shirley Ho has led the first application of deep 3D convolutional neural networks in astrophysics and has since pushed forward the adoption of modern deep learning methods in the astrophysics community. More recently, Shirley Ho has concentrated her effort on accelerating simulations with artificial intelligence, creating foundational models for science, and developing novel techniques in interpretable machine learning.