Go to main site


Machine-learning of density functionals for applications in molecules and materials


Event details

Date and time 20.02.2018 16:1517:15  
Place and room
Speaker Prof. Kieron Burke (University of California, Irvine)
Category Conferences - Seminars

This lecture is designed to be accessible to a wide variety of backgrounds.
In the first part, I will briefly review density functional theory and why it is important to many branches of modern physical science.  I will also review machine learning and its recent applications to molecules and materials.
In the second half,  I will show how, in collaboration with computer scientists at TU Berlin, we have used a specific type of machine-learning, called kernel ridge regression, to find more accurate and powerful approximate density functionals than any made by humans.  
For more background, see here.

14ème NCCR MARVEL "Distinguished Lecture"

Si vous désirez rencontrer le Prof. Burke, veuillez contacter Nathalie Jongen.