PhD Studentship - Optimisation Algorithms of Physical Neural Networks

About the Project

The optimisation algorithm of neural networks, backpropagation, is considered impractical for biological systems and neuromorphic computing.

The recent success of deep learning has raised concerns about its energy consumption. To address this issue, researchers have started exploring physical neural networks (PNNs), which leverage the inherent physical properties of materials for information processing, rather than relying solely on simulations. However, optimizing PNNs remains challenging, and their use is currently limited to simple benchmarks. This project aims to overcome these limitations by integrating standard modeling techniques, such as neural ordinary differential equations (neural-ODE), meta-learning algorithms, and unconventional optimization methods that can be adapted to physical systems. The research will be conducted in collaboration with scientists from Imperial College London and the University of York.

Supervisor Bio

Dr. Luca Manneschi is a passionate young lecturer willing to make impactful contributions to machine learning and neuromorphic computing. His research focuses on neural networks, particularly in the definition of optimisation algorithms for dynamical systems and data stochasticity.

About the Department

99 percent of our research has been rated as world-leading or internationally excellent. We are rated as 8th nationally for the quality of our research environment, showing that the Department of Computer Science is a vibrant and progressive place to undertake research.

Candidate Requirements

• Master's degree or 2.1 undergraduate degree in a relevant topic (Computer Science, Physics, Mathematics etc.).
• Experience with machine learning, particularly neural networks.
• Programming experience in Python or MATLAB.
• If English is not your first language, you must have an IELTS score of 6.5 overall, with no less than 6.0 in each component.

How to apply

To apply for a PhD studentship, applications must be made directly to the University of Sheffield using the Postgraduate Online Application Form. Make sure you name Luca Manneschi as your proposed supervisor.

Information on what documents are required and a link to the application form can be found here - www.sheffield.ac.uk/postgraduate/phd/apply/applying

The form has comprehensive instructions for you to follow, and pop-up help is available.

Your research proposal should:

• Be no longer than 3 A4 pages, include references
• Outline your reasons for applying for this studentship
• Explain how you would approach the research, including details of your skills and experience in the topic area

You are encouraged to contact Luca Manneschi beforehand to discuss the project.

Funding notes

This PhD studentship will cover standard UK home tuition fees and provide a tax-free stipend at the standard UK Research Council rate (currently £19,237 for the 2024/25 academic year) for 3.5 years. If you are an overseas student, you are eligible to apply but you must have the means to pay the difference between the UK and overseas tuition fees by securing additional funding or self-funding. Further information on international fees can be found here: www.sheffield.ac.uk/new-students/tuition-fees/fees-lookup.

Advert information