Geometric Principles for Machine Learning Physical Systems
Add to your list(s)
Download to your calendar using vCal
If you have a question about this talk, please contact div-c.
From classical mechanics, we know that mathematical descriptions of dynamical systems are deeply rooted in topological spaces defined by non-Euclidean geometry. In this talk we will investigate how these structure-rich, geometric representations could be key to improving generalization and parsimony when using machine learning to model physical systems from data.
This talk is part of the Engineering - Dynamics and Vibration Tea Time Talks series.
This talk is included in these lists:
Note that ex-directory lists are not shown.
|