Post

University of York | PhD in Neural Cellular Automata for Top-Down Engineering of Self-Organising Systems

Led by supervisor Dr. James Stovold, the project aims to solve a fundamental challenge in complexity science, how to systematically program micro-level local rules so that a system reliably "grows" into a specific, desired macro-level global behavior.

University of York | PhD in Neural Cellular Automata for Top-Down Engineering of Self-Organising Systems

About the Project

Self-organisation is a property of many natural systems, where local interactions among individuals give rise to patterns and behaviours at the global level—for example, flocks of birds collectively avoiding a predator, or the collective decision-making process of honey bees’ nest site selection [1]. In computer science, we have long sought out the levels of robustness and resilience that is prevalent in nature, and self-organising behaviour appears to be a way of achieving this. Early attempts, however, often ran into issues where engineering the emergent patterns was more challenging than initially expected [2], typically due to how sensitive the global patterns are to small changes in the local rules.

With the introduction of the Neural Cellular Automata (NCA) [3,4], however, we have a mechanism for designing behaviour at the global level and deriving the local rules using a neural network toolbox. Recent advances are helping us to better understand how the NCA works [5], making this the perfect time to apply NCAs to other areas.

This project will investigate how NCAs can be applied within computer science and more broadly, developing new variants of the NCA model as required. Depending on the interests of the student, the focus could be on any one of a wide range of applications areas, including swarm robotics, modelling neuronal growth, retinal cell differentiation, self-healing computer chips, adaptive reservoir computers, among many others.

Students should indicate which application areas they are most interested in pursuing and why.

Training and support

You’ll receive training and guidance in research, writing and presenting skills to support your development during your PhD. You’ll also cover topics such as employability skills, research management and leadership, and graduate teaching assistant training.

In addition, York Graduate Research School works alongside the Department to offer high quality training, peer to peer support, professional development advice, and opportunities to engage others with your research.

Location

Become part of our vibrant community and contribute to inspirational and life-changing research.

You will be based in the Department of Computer Science at the University of York - an exciting and welcoming hub for innovation and collaboration with a modern and inclusive working environment. In our lakeside home on Campus East, you’ll benefit from world-class laboratories and collaboration spaces.

The University of York is located a short distance from York city centre. Our historic city is consistently voted as one of the friendliest, safest and best places to live in the UK.

Entry requirements

  • This funded PhD opportunity is open to individuals eligible to pay tuition fees at the UK (Home) rate.
  • You should hold or expect to achieve the equivalent of at least a UK upper second class degree in a relevant discipline (e.g. physics, computer science, mathematics).
  • We are willing to consider your application if you do not fit this profile, providing you are able to demonstrate that you have sufficient knowledge and experience to succeed on the programme.
  • We’re sorry, on this occasion this opportunity is not available to international students, or to individuals who wish to study via distance learning.

Contact us

If you have any questions about this opportunity, please email: james.stovold@york.ac.uk

References

[1] Camazine S, et al. (2002) “Self-organization in biological systems”, Princeton University Press

[2] Stepney S, Polack F, and Turner H (2006) “Engineering Emergence”, Proc. IEEE ICECCS 2006

[3] Mordvintsev A, Randazzo E, Niklasson E, Levin M (2020) “Growing Neural Cellular Automata”, Distill

[4] Stovold J (2023) “Neural Cellular Automata Can Respond to Signals”, Proc. ALIFE 2023, MIT Press

[5] Stovold J, et al. (2026) “Visualising the Attractor Landscape of Neural Cellular Automata”, Proc. ALIFE 2026, MIT Press

Application and more details: https://www.findaphd.com/phds/project/neural-cellular-automata-for-top-down-engineering-of-self-organising-systems/?p197990

Desktop View

This post is licensed under CC BY 4.0 by the author.