CCB Seminar: Yuanzhao Zhang, Ph.D.

Date


Yuanzhao Zhang, Ph.D., Santa Fe Institute

Physics-Uninformed Machine Learning

How much can we learn about a dynamical system when models are unavailable and data is limited? In the first half of this talk, I will pose basin prediction in multistable systems as a challenging task to probe out-of-domain generalization in neural networks. Surprisingly, reservoir computers (a class of simplified recurrent neural networks) without relevant physics baked in can often extrapolate and reconstruct basins not seen during training. In the second half of the talk, I will discuss time-series foundation models’ ability to forecast a new dynamical system based only on a short context trajectory. We find that foundation models excel at zero-shot forecasting and often utilize context parroting as a key mechanism to forecast chaotic systems. Exploring zero-shot forecasting strategies beyond parroting can provide insights into how artificial and natural intelligence learn from limited data.

Advancing Research in Basic Science and MathematicsSubscribe to Flatiron Institute announcements and other foundation updates

privacy consent banner

Privacy preference

We use cookies to provide you with the best online experience. By clicking "Accept All," you help us understand how our site is used and enhance its performance. You can change your choice at any time here. To learn more, please visit our Privacy Policy.