Research Overview

Like Richard Feynman, I believe that ‘what I cannot create, I do not understand’ (Feynman, 1988). Therefore, I work to develop machines that learn and think like people, leveraging our most fundamental models of cognition and behaviour. I have worked on artificial intelligence from first principles, developing fundamental descriptions of intelligence in natural systems and advancing therefrom toward scalable, biomimetic, aligned artificial agents. I am hopeful that this research program will help us unlock the next generation of AI systems, which are robust and adaptive, safe and trustworthy, data-efficient and environmentally friendly—with transformative advantages for society and scientific discovery.

This podcast summarises my research and interests. For an up-to-date list of publications please see my Google Scholar profile.

Collaborate

I am always looking for potential collaborators: if this is you, please drop me a quick note.

Personal Background 🌍

• I was born in Japan and lived in 8 different countries... and counting!

• I spent my teens living in Luxembourg, where I was at one of the European Schools.

• I then moved to Lausanne, Toronto and Cambridge (UK) to study Mathematics for Bachelor's and Master's .

• I then became interested in artificial intelligence so I moved to London to learn about intelligence in the brain.

• I stayed in London for a few years working as a PhD student in Mathematics and Neuroscience.

Bio

I am a Machine Learning researcher at VERSES AI and a visiting postdoc in Bernhard Schölkopf's group at the ELLIS Institute Tübingen. Before that, I was a PhD student with Greg Pavliotis and Karl Friston jointly at Imperial College London and UCL, and a student in the Mathematics of Random Systems CDT run by Imperial College London and the University of Oxford. I completed an MRes in Brain Sciences at UCL, an MASt in Pure Mathematics at the University of Cambridge, and a BSc in Mathematics at EPFL and the University of Toronto. My work is supported by VERSES.