← all projects
ARIA Opportunity Space: Nature Computes Better
AI for Understanding Human Cognition
We are developing AI technology to understand how the human brain performs intuitive physics calculations, like predicting where a thrown ball will land. Our approach uses interpretable variational encoders (IVE) - a specialized neural network originally developed for astrophysics research that can find compact, meaningful representations in complex data. By applying this technique to brain imaging data from physics prediction tasks, we aim to discover the fundamental building blocks the brain uses to understand physics. This cross-disciplinary research could advance both our understanding of human intelligence and our ability to build AI systems that learn and generalize like humans do.
Hiranya Peiris' Lab
University of Cambridge
,
Cambridge
Peiris Lab
↗
Jonathan holds a DPhil in Machine Learning from Oxford, where he was supervised by Prof. Lord (Lionel) Tarassenko. During his DPhil, he designed, built, and open-sourced world-leading deep learning models for quantitative sleep monitoring from wearables. These are currently being evaluated in clinical studies for the longitudinal monitoring of linked health conditions including insomnia and depression. Alongside his DPhil, he has spent several years working in industry as an AI researcher/engineer at HealthTech companies LIO and Sanome. There he helped to develop several AI-enabled medical devices which have been deployed in healthcare systems in the UK and US. (Personal website: https://joml.io)
Hiranya Peiris
Professor of Astrophysics
Hiranya Peiris holds the Cambridge Professorship of Astrophysics (1909). She is best known for her work on the cosmic microwave background radiation, and creating interdisciplinary links between cosmology and high-energy physics. She received the 2018 Breakthrough Prize in Fundamental Physics. Ray Dolan is Mary Kinross Professor of Neuropsychiatry at UCL and Director of UCL-Max Planck Centre for Computational Psychiatry and Ageing. His research addresses the neurobiology of emotion and decision making, including how decision making breaks down in neurological and psychiatric disease. Miles Cranmer is an Assistant Professor at the University of Cambridge, where he develops AI-driven approaches to scientific discovery in physics and astronomy. His group works on large-scale foundation models for scientific data, and open-source tools such as PySR for symbolic regression. Andrew Pontzen is a Professor of Physics at Durham University, where he works primarily on how structures form in the universe. He is also author of The Universe in a Box which covers the increasing use of computer technology and AI in astrophysics.
Ray Dolan
Kinross Professor of Neuropsychiatry, University College London
Miles Cranmer
Assistant Professor, Cambridge
Andrew Pontzen
Professor in the Department of Physics, University of Durham
