Keith Butler - Applied machine learning for accelerated materials design and analysis
|Starts:||12:00 28 Jan 2020|
|Ends:||13:00 28 Jan 2020|
|What is it:||Seminar|
|Organiser:||Department of Mathematics|
|Who is it for:||University staff, External researchers, Current University students|
Join us for this research seminar, part of the SQUIDS (Statistics, quantification of uncertainty, inverse problems and data science) seminar series.
Abstract: I will present work showing how the SciML group at Rutherford Appleton Laboratory is using machine learning to discover new materials and to accelerate data analysis at some of the UK's large scientific facilities. By combining deep and shallow learning approaches with heuristic screening we have developed approaches to search through some of the vast combinatorial space of possible materials – I will discuss some recent examples using this approach to design new photocatalysts and dielectric materials. I will also show how we apply deep neural networks (DNNs) to understand the data collected at the ISIS neutron and muon source, concentrating on our efforts to understand and interpret the DNNs in order to accelerate analysis and attempt to find new physics.
Organisation: Rutherford Appleton Laboratory
Travel and Contact Information
Frank Adams 1
Alan Turing Building