Neuromorphic computing is at the forefront of machine learning research, aiming to tackle the ever growing energy consumption of modern AI applications. By using physical systems as a 'reservoir' data can be transformed to a representation that is easier to classify or predict in an energy efficient manner.
About the Supervisor
Dr Ellis' research focused on developing energy efficient machine learning algorithms and systems based on neuromorphic computing. In particular, he is interested in developing models of physical systems that can be utilised as machine learning processing devices, such as devices for physical reservoir computing or neuromorphic hardware based on magnetic systems.
Project Description
This project aims to develop novel approaches for physical reservoir computing and it will explore the theoretical framework of advanced read-out, training and connectivity methods for spintronic reservoirs. Recent advances in reservoir computing with our group has highlighted the power of sparse output methods (https://arxiv.org/abs/1912.08124) and connecting multiple reservoirs for tasks with multiple timescales (https://arxiv.org/abs/2101.04223) but their application to physical reservoir systems has not been proven. This project will study these techniques applied to models of magnetic reservoirs with a view to apply these to state-of-the-art machine learning tasks to demonstrate the potential of reservoir computing in real life. To aid the development of these techniques it may be necessary to develop neural ODE models of the physical reservoirs to reduce the computational complexity of the physical models.
About the Department
99 percent of our research is rated in the highest two categories in the REF 2021, meaning it is classed 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.
This PhD will join a strong inter-disciplinary research collaboration crossing the Departments of Computer Science and Materials Science covering both theoretical and experimental research into neuromorphic computing.
Entry Requirements
The candidate should be self-motivated and hold at least a 2:1 degree in computer science, mathematics, physics or another relevant subject area, with a strong computational and mathematical background.
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 Dr Matthew Ellis as your proposed supervisor.
Information on what documents are required and a link to the application form can be found here - https://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 4 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