Harnessing Chaos and Predicting the Unpredictable with A.I.: A Community Lecture with MIchelle Girvan
*The video for this event does not play well in Firefox. Please switch browsers if the audio and video are out of synch.
In recent years, machine learning methods such as "deep learning" have proven enormously successful for tasks such as image classification and voice recognition. Despite their effectiveness for big-data classification problems, these methods have had limited success predicting "chaotic" systems like those we see in weather, solar activity, and even brain dynamics. For decades, scientists have understood that the "butterfly effect" makes long-term prediction impossible for these chaotic systems. In this talk, physicist Michelle Girvan discusses how a Reservoir Computer (RC) — a special kind of artificial neural network — can draw on its own internal chaotic dynamics in order to forecast systems like the weather, far beyond the time horizon of other methods. The RC provides a knowledge-free approach because it builds forecasts purely from past measurements without any specific knowledge of the system dynamics. By building a new approach that judiciously combines the knowledge-free prediction of the RC with a knowledge-based model, she demonstrates a further, dramatic, improvement in forecasting chaotic systems.
Michelle Girvan is an Associate Professor in the Department of Physics and the Institute for Physical Science and Technology at the University of Maryland, College Park. She is also a member of the External Faculty at the Santa Fe Institute. Her research operates at the intersection of statistical physics, nonlinear dynamics, and computer science and has applications to social, biological, and technological systems.
Reserve your free tickets through The Lensic Box Office online or call 505.988.1234. Santa Fe residents are encouraged to attend in person. Those unable to attend can stream the lecture from our YouTube page.
SFI’s 2018 Community Lecture Series is generously underwritten by Thornburg Investment Management, with additional support provided by The Lensic Performing Arts Center and the Enterprise Holdings Foundation.