Hannes Kneiding is a PhD Candidate at the Hylleraas Centre for Quantum Molecular Sciences, Department of Chemistry, UiO. He is also part of the CompSci doctoral program. He will be defending his thesis for the degree of PhD, which was submitted for evaluation on the 27th of May of 2024.
From the CompSci team we wish you good luck and all the best in your future endeavors!
→ Read more about the disputation in the website of the Department of Chemistry
Programme
09:15 – Trial lecture: "Large language models for chemistry - passing fad or transformative tool?" – Auditorium 4, Chemistry building
13:15 – Disputation: "Complex Learning - Machine learning approaches for transition metal complexes" – Auditorium 1, Chemistry building
This event is open for everyone. No registration needed.
The Disputation will be live streamed for everyone else.
The livestream will be activated 15 minutes before the Defense starts.
PhD candidate
Research group | Hylleraas Centre for Quantum Molecular Sciences RT5
Main supervisor | David Balcells
Co-supervisors | R. De Bin & T.B. Pedersen
Affiliation | Department of Chemistry, UiO
Contact | hanneskn@uio.no
Adjudication committee
Prof. Kim Jelfs, Imperial College London
Prof. Kjell Jorner, ETH Zürich
Prof. Reidar Lund, University of Oslo
Chair of defense
Prof. Harald Walderhaug, Department of Chemistry, University of Oslo
Short summary
Complex Learning - Machine learning approaches for transition metal complexes
Transition metal complexes (TMCs) are essential for a large range of different applications in renewable energies, energy storage, medicinal chemistry and more. Finding TMCs that have optimal properties for such applications is an expensive and time-consuming task as it traditionally requires experiments. Computer-based methods can accelerate this process by screening a large number of TMCs for promising candidates beforehand. Particularly machine learning approaches that leverage existing data have recently drawn a lot of attention. However, most research in this field focuses on small organic molecules which are easier to handle due to their simpler chemistry.
In this thesis I present four different and novel machine learning approaches, specifically designed for their application to TMCs. In particular they are: (1) a neural network leveraging quantum chemistry informed graph representations, (2) a genetic algorithm performing directional and multi-objective optimization, (3) a set of autocorrelation descriptors capturing bond-bond and atom-bond relationships, and (4) a generative neural network for the generation of novel ligands with specific properties. In addition to these methods I also present two TMC datasets and discuss how they can be exploited for the computer-aided discovery of TMCs.
