![[Search]](/static/images/search.gif){kind=small}
![[A-Z Index]](/static/images/az.gif){kind=small}
![[Contact]](/static/images/contact.gif){kind=small}
![[University of Cambridge]](/static/images/identifier2.gif){kind=small}
![[Talks.cam]](/static/images/talkslogosmall.gif)
Monday 19 April 2021, 16:30-17:30
Data-Efficient Machine Learning with Chemical and Physical Priors
- đ¤ Speaker: Johannes Margraf, Fritz-Haber-Institut der MPG
- đ Date & Time: Monday 19 April 2021, 16:30 - 17:30
- đ Venue: virtual ZOOM meeting ID: 263 591 6003, Passcode: 000042, https://us02web.zoom.us/j/2635916003?pwd=ZlBEQnRENGwxNmJGMENGMWxjak5nUT09
Questions? Contact
Bingqing Cheng
Abstract
While machine learning is often discussed in a ‘big data’ context, for many chemical applications the generation of large reference databases can be prohibitive. I will talk about how the data-efficiency of machine learning models can be improved by using chemical or physical priors. In particular, I will discuss the role of size-extensivity, physical baseline models and hybrid approaches that integrate electronic structure theory and machine learning.
Series This talk is part of the Machine learning in Physics, Chemistry and Materials discussion group (MLDG) series.
Included in Lists
- Hanchen DaDaDash
- Lennard-Jones Centre external
- Machine learning in Physics, Chemistry and Materials discussion group (MLDG)
- virtual ZOOM meeting ID: 263 591 6003, Passcode: 000042, https://us02web.zoom.us/j/2635916003?pwd=ZlBEQnRENGwxNmJGMENGMWxjak5nUT09
Note: Ex-directory lists are not shown.