[Turing-Southampton] AI3SD Winter Seminar Series: #3 - Enhancing Experiments through Machine Learning - 161220

[Susan Davies]

***apologies if you receive this more than once***

Circulated on behalf of Samantha Kanza

The AI 4 Scientific Discovery Network (www.ai3sd.org<https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.ai3sd.org%2F&data=04%7C01%7C%7C59c207a9bdd04bc1776008d8960c82f3%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637424327757451252%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=PXYFPTm9a%2Fy%2BkkhCSZlWMbv6beaKYvnTlxcqMMQ6Af8%3D&reserved=0>) are delighted to announce the third event in our Winter Seminar Series: Enhancing Experiments through Machine Learning on the 16th December 2020 - 14:00-16:45

You can sign up for this event here: https://ai3sd-winter-series-161220.eventbrite.co.uk<https://ai3sd-winter-series-161220.eventbrite.co.uk/>

This event consists of three talks:

Interpretable machine learning for materials design and characterization - Dr Keith Butler<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fkeeeto.github.io%2Fabout%2F&data=04%7C01%7C%7C59c207a9bdd04bc1776008d8960c82f3%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637424327757451252%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=vRXxg1bPhL1rV%2F6Fiehw1g6AdKlzQG8esKZ8jUHtFxY%3D&reserved=0> (STFC)
In a plenary lecture at a recent international conference, one leading researcher in theoretical chemistry remarked "at least 50% of the machine learning papers I see regarding electronic structure theory are junk, and do not meet the minimal standards of scientific publication", specifically referring to the lack of insight in many publications applying ML in that field. But is knowledge inevitably lost in machine learning studies, if not how can it be extracted and how does this apply to machine learning in the context of materials science? In this talk I will look at how we can open up black box machine learning models, to understand the results and gain confidence in predictions. I will present topical examples from designing new dielectric crystals, understanding inelastic neutron scattering data and trusting deep neural networks for tomographic reconstruction. By understanding how and why these models work, we can trust the results and even discover new physical relationships.

When charge transport data are a worm - a transfer learning approach for unsupervised data classification - Professor Tim Albrecht<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.birmingham.ac.uk%2Fstaff%2Fprofiles%2Fchemistry%2Falbrecht-tim.aspx&data=04%7C01%7C%7C59c207a9bdd04bc1776008d8960c82f3%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637424327757461207%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=W5VxZ0i3Pok0Gke0SpRuF1I58efs2ItaRsUpQIX6tHU%3D&reserved=0> (University of Birmingham)
Advanced data analysis methodologies, and in particular dimensionality reduction techniques, are now used more and more widely in the single-molecule charge transport community. They allow for comprehensive exploration of large datasets, where data display significant variance and sometimes contain (unknown) sub-populations. To this end, unsupervised approaches, which do not rely on class labels or pre-defined expectations can be advantageous. Multi-Parameter Vector Classification (MPVC) is one example and PCA-based methods have also been employed in this context [1,2,3]. We have recently shown how Transfer Learning may be employed to identify and quantify hidden features in single-molecule charge transport data [3]. Using open-access neural networks such as AlexNet, trained on millions of seemingly unrelated image data, feature recognition then does not require network training with application-specific data. Instead, the network recognises features in the input that it had learned in other contexts and, for example, identifies different shapes in conductance-distance traces as images of different worm species. Thus, our results show how Deep Learning methodologies can readily be employed for unsupervised data classification, even if the amount of problem-specific, 'own' data is limited.

[1] M Lemmer, MS Inkpen, K Kornysheva, NJ Long, T Albrecht, "Unsupervised vector-based classification of single-molecule charge transport data", Nat. Comm. 2016, 7, 12922.
[2] T Albrecht, G Slabaugh, E Alonso, SMMR Al-Arif, "Deep learning for single-molecule science", Nanotechnology 2017, 28 (42), 423001.
[3] A Vladyka, T Albrecht, "Unsupervised classification of single-molecule data with autoencoders and transfer learning", Mach. Learn.: Sci. Technol. 2020, 1, 035013.

Prediction in organometallic catalysis - a challenge for computational chemistry - Dr Natalie Fey<https://eur03.safelinks.protection.outlook.com/?url=http%3A%2F%2Fwww.bris.ac.uk%2Fchemistry%2Fpeople%2Fnatalie-fey%2Findex.html&data=04%7C01%7C%7C59c207a9bdd04bc1776008d8960c82f3%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637424327757461207%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=oEOlhUDLut5Mm6Hk2ZKZRiEF%2FjcrFC89Nyhd68r6w7w%3D&reserved=0> (University of Bristol)
Computational results are now routinely used to contribute to the interpretation of experimental data, including for the confirmation of mechanistic postulates, but their contribution to substantial predictions made before experiments remains the exception [1], at least in the area of organometallic catalysis. More effective use of what we know about chemical reactions, regardless of whether the information was generated from experiment or calculation, will clearly play a role in moving towards this kind of ab initio prediction in this field. Here the adoption of statistics and data science into the chemical sciences are proving crucial and we have built large databases of parameters characterising ligand and complex properties in a range of different environments [2-6]. In this session, I will use examples drawn from our recent work, including the early stages of our development of a reactivity database, to illustrate this approach and discuss why organometallic catalysis is such a challenging yet rewarding area for prediction.
Website: https://feygroupchem.wordpress.com/<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Ffeygroupchem.wordpress.com%2F&data=04%7C01%7C%7C59c207a9bdd04bc1776008d8960c82f3%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637424327757471164%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=VoKoAKlnQUoe0wRv3zaDxIaVtfSzJr2lbQs4tJHGDxo%3D&reserved=0>

References:
1. J. Jover, N. Fey, Chem. Asian J., 9 (2014), 1714-1723; D. J. Durand, N. Fey, Chem. Rev., 119 (2019), 6561-6594.
2. A. Lai, J. Clifton, P. L. Diaconescu, N. Fey, Chem. Commun., 55 (2019), 7021-7024.
3. O. J. S. Pickup, I. Khazal, E. J. Smith, A. C. Whitwood, J. M. Lynam, K. Bolaky, T. C.
King, B. W. Rawe, N. Fey, Organometallics, 33 (2014), 1751-1791.
4. J. Jover, N. Fey, J. N. Harvey, G. C. Lloyd-Jones, A. G. Orpen, G. J. J. Owen-Smith, P.
Murray, D. R. J. Hose, R. Osborne, M. Purdie, Organometallics, 29 (2010), 6245-6258.
5. J. Jover, N. Fey, J. N. Harvey, G. C. Lloyd-Jones, A. G. Orpen, G. J. J. Owen-Smith, P.
Murray, D. R. J. Hose, R. Osborne, M. Purdie, Organometallics, 31 (2012), 5302-5306.
6. A. I. Green, C. P. Tinworth, S. Warriner, A. Nelson, N. Fey, Chem. Eur. J. 2020, Accepted Article, DOI: 10.1002/chem.202003801.

Further details of the rest of the seminar series can be found on our website: https://www.ai3sd.org/winter-seminar-series-2021<https://eur03.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.ai3sd.org%2Fwinter-seminar-series-2021&data=04%7C01%7C%7C59c207a9bdd04bc1776008d8960c82f3%7C4a5378f929f44d3ebe89669d03ada9d8%7C0%7C0%7C637424327757471164%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C1000&sdata=GB3l3KNCrMxNhceriQGBmrgaZ1cJ6%2BjNWPB7exaBYT8%3D&reserved=0>. We are still finalising the details of some of the seminars, and emails/eventbrites will be sent out as each seminar is finalised. If you are interested in getting involved with our seminar series then please get in touch with us on info at ai3sd.org<mailto:info at ai3sd.org>.

Best Wishes,

Dr Samantha Kanza
Research Fellow & Enterprise Fellow Network+ Coordinator of the AI3 Science Discovery Network+
Faculty of Engineering and Physical Sciences
University of Southampton


-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.ecs.soton.ac.uk/pipermail/turing-southampton/attachments/20201201/1ae4a28f/attachment-0001.html