"AI in chemistry and beyond: Highlights in the field" seminar by Logan Ward "active learning for molecular design"

Thumbnail

Event details

Date 11.10.2022 15:1516:15  
Speaker Logan Ward is an Assistant Computational Scientist at Argonne National Laboratory. His Ph.D. is in Materials Science of Engineering from Northwestern University, where he focused on developing machine-learning-based techniques for predicting material properties. He works on developing the software and data infrastructure necessary to make machine learning more accessible to all scientists.
Location Online
Category Conferences - Seminars
Event Language English

Fully realizing the ability of automated laboratories and exascale computing systems to design materials requires removing humans from the process. In this talk, we cover the basics of machine learning approaches to replacing the process of creating ideas for materials to test, inferring if they are feasible, and designing experiments. We will explain the theory behind such techniques, give some practical examples from recent literature, and identify example software as starting points for using these techniques in your own research.

References
[1] Agarwal, G., Doan, H. A., Robertson, L. A., Zhang, L., & Assary, R. S. (2021). Discovery of energy storage molecular materials using quantum chemistry-guided multiobjective Bayesian optimization. Chemistry of Materials: A Publication of the American Chemical Society33(20), 8133–8144. https://doi.org/10.1021/acs.chemmater.1c02040
[2] Schwalbe-Koda, D., & Gómez-Bombarelli, R. (2019). Generative models for automatic chemical design. In arXiv [cs.LG]. http://arxiv.org/abs/1907.01632
[3] Ward, L., Dandu, N., Blaiszik, B., Narayanan, B., Assary, R. S., Redfern, P. C., Foster, I., & Curtiss, L. A. (2021). Graph-based approaches for predicting solvation energy in multiple solvents: Open datasets and machine learning models. The Journal of Physical Chemistry. A125(27), 5990–5998. https://doi.org/10.1021/acs.jpca.1c01960

Practical information

  • Informed public
  • Free

Organizer

  • Kevin Maik Jablonka,  Puck van Gerwen, Philippe Schwaller, Andres Bran, Jeff Guo

Contact

  • Kevin Maik Jablonka,  Puck van Gerwen, Philippe Schwaller, Andres Bran, Jeff Guo

Tags

MLseminar1

Share