Artificial intelligence (AI) applications are transformative, but they are becoming increasingly unsustainable. Many AI models require extensive training with large model sizes. As an alternative reservoir computing exploits random fixed networks to transform data to simplify training. By creating structure within these networks, much like the natural structure in the brain, different properties can be tailored. This project aims to explore how combining network modules with diverse properties can be used to create easy to train AI models capable of solving challenging, real-world problems. It will involve the analysis of echo-state network models to determine how small network structures can be adapted to maximise properties (e.g memory). From these ‘modules’ we will then investigate how these can be combined to create enhanced ‘deep reservoir systems’ ( www.frontiersin.org/articles/10.3389/fams.2020.616658 ) and demonstrate these on real-world tasks, such as activity recognition from smart sensor data. Supervisor Bio Dr. Matthew Ellis’ research intersects machine learning and physics; looking to better integrate advances in both to create new paradigms for computing. With a background in theoretical physics, he looks at how unconventional computing systems can be used to create energy efficient hardware for AI applications. He has particular interests in unconventional machine learning algorithms, computational modelling and how studying the brain can inspire new architectures. About the Department/Research Group The candidate will join the Bio-Inspired Machine Learning Lab, jointly led by Dr. Ellis and Prof. Eleni Vasilaki. They join a strong interdisciplinary collaboration crossing the Computer Science and Materials Science covering both theoretical and experimental research into neuromorphic computing. The department has a track record of research excellence; ranking 8 th nationally for research environment quality and 99% of our research rated world-leading or internationally excellent. Candidate Requirements Minimum 2.1 Bachelor’s or Master’s degree in a relevant discipline (e.g., Computer Science, Physics, etc), or equivalent. Self-motivated with experience in machine learning and/or computational modelling. Strong programming skills; ideally Python. If English is not your first language: an IELTS score of 6.5 overall, with no less than 6.0 in each component. How to apply Please note that this studentship is one of three projects advertised with Dr Matt Ellis. Applicants should only apply for one they are most interested in. Applications must be made directly to the University of Sheffield using the Postgraduate Online Application Form with Dr Matt Ellis named as your proposed supervisor. You should include a short (up to 3 A4 pages) research statement that outlines your reasons for applying for this studentship and explains how you would approach the research, including details of your skills and experience in the topic area. 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 Funding notes The 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 2024/25) for 3.5 years. Overseas students 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 can be found here: www.sheffield.ac.uk/new-students/tuition-fees/fees-lookup £19,237 - please see advert