Young Researcher’s Workshop on Machine Learning for Materials Science
Location : CECAM-FI
May 6, 2019 - May 10, 2019
The influx of machine learning (ML) algorithms from computer science into computational materials science (MS) have led to developments of novel computational methodologies and opened up novel routes to addressing outstanding problems. Over the past decade, seminal works have shown how to employ ML algorithms in global structure search [1,2], to predict stabilities of molecules  and solids , or target materials with particular functional properties [5,6]. Much has become known about the performance and versatility of ML techniques such as kernel ridge [3,4] and Gaussian process  regression, neural networks [5,8], genetic algorithms  and Bayesian approaches , with recent advances too numerous to mention. Materials descriptors that facilitate ML for both molecules and solids are growing ever more sophisticated [9,10] and have dramatically improved the accuracy of ML predictions.
The successes of this rapidly developing research field have also opened many questions on how to further enhance current methodology. Is learning materials descriptors the best long-term strategy, and should ML techniques be combined in workflows for maximum benefit? While it is now possible to predict materials properties given the structure, how can we tackle the inverse problem of predicting chemically-meaningful material structures given desired properties?
Our workshop is aimed at nurturing the ground for the next generation of scientists, which will be able to proactively and efficiently exploit data-driven techniques in the field of materials modelling. To this end, we aim to bring together young researchers, experts from computer science, and world-wide renown researchers applying ML in computational physics or chemistry. Didactic introductory lectures as well as hands on tutorials will allow to introduce the researchers to a broad range of machine learning techniques and algorithms.
During the workshop, expert practitioners employing ML methods in materials science will furthermore provide an overview of the cutting-edge applications. Computer scientists, who are however familiar with materials science problems, will further introduce additional algorithms and techniques that could help overcome the shortcomings of current methodologies and develop approaches beyond the state-of-the-art. Timetabled discussion sessions will be organised in order to promote cross-talk and nurture scientific advancements; these will be focusing on key issues such as:
- generalising materials descriptors;
- inverse learning problems and generative models;
- latent space and reinforcement learning approaches;
- quantifying uncertainty in ML predictions;
- direct application of ML to MD simulations.
2 day ML school (6-8 May): introductory lectures and hands-on computer session on ML methods and descriptors.
2 day ML workshop (8-10 May): invited and contributed talks, followed by round-table discussions and poster session.
Website & registration opens: 1 February 2019
Abstract submission: 10 March 2019.
Registration and abstracts at: ml4ms2019.aalto.fi
Participant confirmation: 15 March 2019
 A. R. Oganov and C. W. Glass, J. Chem. Phys. 124, 244704 (2006).
 L. J. Nelson, G. L. W. Hart, F. Zhou, and V. Ozolins, Phys. Rev. B 87, 035125 (2013).
 M. Rupp, A. Tkatchenko, K.-R. Müller, and O. A. von Lilienfeld, Phys. Rev. Lett. 108, 058301 (2012).
 F. A. Faber, A. Lindmaa, O. A. von Lilienfeld, and R. Armiento, Phys. Rev. Lett. 117, 135502 (2016).
 E. O. Pyzer-Knapp, K. Li, and A. Aspuru-Guzik, Adv. Fun. Mat. 25, 6495 (2015).
 A. Seko, A. Togo, H. Hayashi, K. Tsuda, L. Chaput, and I. Tanaka, Phys. Rev. Lett. 115, 205901 (2015).
 A. P. Bartok, M. C. Payne, R. Kondor, and G. Csanyi, Phys. Rev. Lett. 104, 136403 (2010).
 J. Behler and M. Parrinello, Phys. Rev. Lett. 98, 146401 (2007).
 H. Huo and M. Rupp, arXiv preprint arXiv:1704.06439 (2017).
Gabor Csanyi (University of Cambridge)