Materials and Megabytes Stanford Materials Computation and Theory Group, Qian Yang's lab at the University of Connecticut

We discuss the paper Learning from Failure: Predicting Electronic Structure Calculation Outcomes with Machine Learning Models with the author Prof. Heather J. Kulik.

Papers discussed in this episode:
(Main discussion) Duan, C.; Janet, J. P.; Liu, F.; Nandy, A.; Kulik, H. J. Learning from Failure: Predicting Electronic Structure Calculation Outcomes with Machine Learning Models. J. Chem. Theory Comput. 2019, 15 (4), 2331–2345. https://doi.org/10.1021/acs.jctc.9b00057.(More on uncertainty metrics in latent space) Janet, J. P.; Duan, C.; Yang, T.; Nandy, A.; Kulik, H. J. A Quantitative Uncertainty Metric Controls Error in Neural Network-Driven Chemical Discovery. Chem. Sci. 2019, 10 (34), 7913–7922. https://doi.org/10.1039/C9SC02298H.(Follow-up paper with active learning) Janet, J. P.; Ramesh, S.; Duan, C.; Kulik, H. Accurate Multi-Objective Design in a Space of Millions of Transition Metal Complexes with Neural-Network-Driven Efficient Global Optimization. 2019. https://doi.org/10.26434/chemrxiv.11367572.v1.Kulik group website: http://hjkgrp.mit.edu/

We discuss the paper Screening billions of candidates for solid lithium-ion conductors: A transfer learning approach for small data with the authors Dr. Ekin Dogus Cubuk and Dr. Austin D. Sendek.

Papers discussed in the episode:
Cubuk, E. D.; Sendek, A. D.; Reed, E. J. Screening Billions of Candidates for Solid Lithium-Ion Conductors: A Transfer Learning Approach for Small Data. J. Chem. Phys. 2019, 150 (21), 214701. https://doi.org/10.1063/1.5093220.Sendek, A. D.; Yang, Q.; D. Cubuk, E.; N. Duerloo, K.-A.; Cui, Y.; J. Reed, E. Holistic Computational Structure Screening of More than 12000 Candidates for Solid Lithium-Ion Conductor Materials. Energy & Environmental Science 2017, 10 (1), 306–320. https://doi.org/10.1039/C6EE02697D.Hinton, G.; Vinyals, O.; Dean, J. Distilling the Knowledge in a Neural Network. arXiv:1503.02531 [cs, stat] 2015.Zhou, Q.; Tang, P.; Liu, S.; Pan, J.; Yan, Q.; Zhang, S.-C. Learning Atoms for Materials Discovery. PNAS 2018, 115 (28), E6411–E6417. https://doi.org/10.1073/pnas.1801181115.Sendek, A. D.; Cheon, G.; Pasta, M.; Reed, E. J. Quantifying the Search for Solid Li-Ion Electrolyte Materials by Anion: A Data-Driven Perspective. arXiv:1904.08996 [cond-mat, physics:physics] 2019.

Our guest on this episode is Dr. Turab Lookman from Los Alamos National Laboratory. The interview took place at the 2018 MRS Fall meeting.

Relevant papers:
Gubernatis, J. E.; Lookman, T., Machine Learning in Materials Design and Discovery: Examples from the Present and Suggestions for the Future. Phys. Rev. Materials 2018, 2 (12), 120301. https://doi.org/10.1103/PhysRevMaterials.2.120301.Rickman, J. M.; Lookman, T.; Kalinin, S. V., Materials Informatics: From the Atomic-Level to the Continuum. Acta Materialia 2019, 168, 473–510. https://doi.org/10.1016/j.actamat.2019.01.051.Lookman, T.; Balachandran, P. V.; Xue, D.; Yuan, R. Active Learning in Materials Science with Emphasis on Adaptive Sampling Using Uncertainties for Targeted Design. npj Computational Materials 2019, 5 (1), 21. https://doi.org/10.1038/s41524-019-0153-8.Xue, D.; Balachandran, P. V.; Hogden, J.; Theiler, J.; Xue, D.; Lookman, T., Accelerated Search for Materials with Targeted Properties by Adaptive Design. Nature Communications 2016, 7, 11241. https://doi.org/10.1038/ncomms11241.

Our guest on this episode is Dr. Patrick Riley from Google Accelerated Science.

Some relevant papers and links:
Riley, P., Practical advice for analysis of large, complex data sets. The Unofficial Google Data Science Blog, www.unofficialgoogledatascience.com/2016/10/practical-advice-for-analysis-of-large.html (2016)Zinkevich, M., Rules of Machine Learning: Best Practices for ML Engineering. https://developers.google.com/machine-learning/guides/rules-of-ml/ (last updated Oct 2018)Wigner, E., The Unreasonable Effectiveness of Mathematics in the Natural Sciences. Communications in Pure and Applied Mathematics, doi:10.1002/cpa.3160130102 (1960)Gulshan, V., Peng, L, Coram, M., Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. The Journal of the American Medical Association, doi:10.1001/jama.2016.17216 (2016)
Google Accelerated Science website: ai.google/research/teams/applied-science/gas

Our guest for this episode is Prof. Dr. O. Anatole von Lilienfeld from the University of Basel.

Some relevant papers:


Huang, B., and von Lilienfeld, O. A., The ‘DNA’ of Chemistry: Scalable Quantum Machine Learning with ‘Amons.’ arXiv:1707.04146, (2017)Ramakrishnan, R., Dral, P. O., Rupp, M., and von Lilienfeld, O. A., Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach. Journal of Chemical Theory and Computation, doi:10.1021/acs.jctc.5b00099 (2015)Rupp, M., Tkatchenko, A., Müller, K.-R., and von Lilienfeld, O. A., Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning. Physical Review Letters, doi:10.1103/PhysRevLett.108.058301 (2012)
Group website: https://www.chemie.unibas.ch/~anatole/

Our guest on this episode is Professor Gábor Csányi from the University of Cambridge.

Some relevant papers:
Bartok, A. P., Payne, M. C., Kondor, R., and Csanyi, G., Gaussian
approximation potentials: the accuracy of quantum mechanics, without the electrons. Physical Review Letters, doi:10.1103/PhysRevLett.104.136403
(2010)Bartok, A. P., Kondor, R., and Csanyi, G., On representing chemical environments. Phys. Rev. B, doi:10.1103/PhysRevB.87.184115 (2013)Braams, B. J., and Bowman, J. M., Permutationally invariant potential energy surfaces in high dimensionality. International Reviews in Physical Chemistry, doi:10.1080/01442350903234923 (2009)