Atomistic Machine Learning between Physics and Data

Add to your list(s) Download to your calendar using vCal

• Prof. Michele Ceriotti, Head COSMO Laboratory
• Wednesday 24 April 2019, 11:00-12:00
• Goldsmiths 1, Lecture Theatre, Department of Materials Science & Metallurgy.

If you have a question about this talk, please contact Nichola Daily.

Statistical regression techniques have become very fashionable as a tool to predict the properties of systems at the atomic scale, sidestepping much of the computational cost of first-principles simulations and making it possible to perform simulations that require thorough statistical sampling without compromising on the accuracy of the electronic structure model.

In this talk I will argue how data-driven modelling can be rooted in a mathematically rigorous and physically-motivated framework, and how this is beneficial to the accuracy and the transferability of the model. I will also highlight how machine learning – despite amounting essentially to data interpolation – can provide important physical insights on the behaviour of complex systems, on the synthesizability and on the structure-property relations of materials.

I will give examples concerning all sorts of atomistic systems, from semiconductors to molecular crystals, and properties as diverse as drug-protein interactions, dielectric response of aqueous systems and NMR chemical shielding in the solid state.

This talk is part of the Materials Modelling Seminars series.

This talk is included in these lists:

• Goldsmiths 1, Lecture Theatre, Department of Materials Science & Metallurgy
• Goldsmiths 1, Lecture Theatre, Department of Materials Science & Metallurgy
• Goldsmiths 1, Lecture Theatre, Department of Materials Science & Metallurgy
• Goldsmiths 1, Lecture Theatre, Department of Materials Science & Metallurgy
• Materials Modelling Seminars
• Mats Sciences Lists

Note that ex-directory lists are not shown.