Biological and artificial intelligence 🧠 at the University of Cambridge, MRC Cognition and Brain Sciences Unit.  I study how cognition in brains and machines can be understood using mathematical models.

To do this, I use a range of techniques borrowed from diverse fields of neuroscience, applied-maths and systems biology. Most of my work involves tying ideas across neurophysiology, developmental biology and AI - with the aim to bridge biological and artificial cognition.

I completed my PhD at Pembroke College in Cambridge under the supervision of Professor Duncan Astle and advise of Dr Petra Vertes. Over this time I've been very fortunate to have numerous international collaborations, with colleagues at ETH Zürich, Harvard, Cardiff and DeepMind. 


I previously trained as a medical doctor and I have an active interest in startups relating to digital health, precision healthcare and data-driven medicine. A few years ago, I co-founded Psynergy Mental Health which is developing better ways to improve mental health in the workplace. We are collaborating with the NHS and Cambridge Enterprise to make our solutions available to the public. I provide consulting services for companies on topics including data science, AI and digital-health related startups. If you are interested, please get in touch here.

Educational background 🏫

University of Cambridge
PhD Computational Neuroscience, Pembroke College (2019-2022)
MRC Cognition and Brain Sciences Unit

University of Cambridge
MPhil Basic and Translational Neuroscience, Robinson College (2016-2017)
Department of Physiology, Development and Neuroscience
MRC Cognition and Brain Sciences Unit

University of Southampton
BMedSc BMBS Medicine (2013-2019)
University Hospital Southampton & Wessex Neurological Centre

 Some recent work 📄

My Google Scholar has my full publication list, but this is some of my most recent highlighted works.

Spatially-embedded recurrent neural networks

Together with Jascha Achterberg, we have recently developed a new model called the spatially-embedded recurrent neural network (seRNN) which provides neural networks with a three-dimensional geometric structure along with communication constraints that we think is a fair reflection of signal propogation in neural circuits. Adding in these fairly simple constraints into the network leads to some neat findings which we hope to publish soon. 

We have presented some of this work at Cognitive Computational Neuroscience Conference 2022 in San Francisco in addition to Bernstein Conference 2022 in Berlin.

Want to learn more? Get in touch with me or follow this link to Jascha's page on the topic.

Generative models of neural networks at the cellular scale

With colleagues at PDN Cambridge and Department of Biosystems Science and Engineering ETH Zürich we set out to learn how to understand the connectivity patterns that exist in neuronal networks at the cellular resolution. The photo on the left shows individual neurons (in pink) that have been grown on a High-Density Microelectrode Array (HD-MEA) system. What you see in green are electrodes that can pick up the electrical signals of the neurons.

Using generative models, we can then work out via simulations what rules best explain the organisation of the networks that develop over time in these networks. You can find our preprint here and we hope it will be in-print soon.

Understanding neurodiversity in brain organisation

It is not easy to know the best way to think about how and why there are individual differences between us as we develop. But one way is to think of it at the level of the brain and ask: what are the similarities and differences that we observe, between us? Even better is to build a model that can actually simulate out these similarities and differences so that we can observe the space of all possible brains that can develop. 

In this work, published in 2021 in Nature Communications, we utilised a technique called generative network modelling to simulate brain connectivity formation in a large sample of neurodiverse children. This work paved the way for a whole lot more research still to come. For a condensed summary, you can see my talk at the University of Edinburgh here.