Automating Scientific Discovery in Physics using Hybrid AI Models

The increasing mathematical intricacy in different subfields of Physics define new barriers the interpretation of more complex physical phenomena and for the creation of new models. In order to tackle this increasing complexity, Physicists will require the support of new tools and methods which can augment and support their analysis and modeling process, exploring other media, beyond the traditional "pen and paper".

Artificial Intelligence techniques emerges as a natural candidate to facilitate the modeling work of Physicist under an increasing complexity scale.

This project will explore the application of natural language processing, machine learning models and automated symbolic-deductive reasoning techniques to support the creation of an analytical modeling assistant for complex systems in Condensed Matter Physics.

As a PhD student you will work at the interface between AI and Physics, understanding and encoding the conceptual complexity involved in the process of developing new models in Condensed Matter Physics, using the extensive palette of tools available in the AI community.

The project will be done in close collaboration and co-supervision of Dr. Alessandro Principi from the School of Physics and Astronomy at the University of Manchester.

Applicants are expected to have:

* An excellent undergraduate degree in Computer Science or Mathematics (or related discipline), and preferably, a relevant M.Sc. degree.
* Confidence and independence in programming complex systems in Java or Python.
* Previous academic or industry experience in Natural Language Processing or Machine Learning (desired).
* Excellent report writing and presentation skills.

Please note that applicants must additionally satisfy the standard requirements for postgraduate studies at the University of Manchester, such as a first-class or high upper-second class (or an equivalent international qualification) and English language qualifications, as stated in the PGR guidelines.

Qualified applicants are strongly encouraged to informally contact Andre Freitas ([Email Address Removed]) to discuss the application prior to applying.