James Nelson

James graduated with a First Class Honours degree in Theoretical Physics from Trinity College in 2016 and soon after joined the group as a PhD student. His research is concerned with applying machine learning to problems in condensed matter physics, specifically, novel material discovery and many-body models. Material discovery offers great opportunities for Machine Learning due to the vast range of potential materials. While in many-body physics, machine learning can speed up solving the models, due to the universality of algorithms such as neural networks to represent any function. Side academic interests include artificial intelligence and philosophy of mind.

Publications

James Nelson, Rajarshi Tiwari and Stefano Sanvito. Machine learning density functional theory for the Hubbard model, Phys. Rev. B 99, 075132 (2019).

James Nelson and Stefano Sanvito. Predicting the Curie temperature of ferromagnets using machine learning. Phys. Rev. Mat. 3, 104405 (2019)

S. Sanvito, M. Zic, J. Nelson, T. Archer, C. Oses, and S. Curtarolo. Machine Learning and High-Throughput Approaches to Magnetism. W. Andreoni and S. Yip (eds) “Handbook of Materials Modeling”. Springer, Cham, 2018.