Nanda Harishankar Krishna

I am a PhD Candidate supervised by Guillaume Lajoie at Mila – Quebec AI Institute and Université de Montréal. My research interests lie at the intersection of Computational Neuroscience and Deep Learning. I am specifically interested in developing a theoretical understanding of how learning shapes computation in brains and artificial neural networks. I also work on building foundation models for neuroscience, with the goal of improving decoding in brain-computer interfaces. My current projects include modelling the effects of learning histories and curricula on compositional generalisation, mechanistically unifying reinforcement learning paradigms using local learning rules, and developing generalisable, real-time decoders for brain-computer interfaces using foundation models of neural activity. Aside from research, I am passionate about teaching, open science and open source software. Currently, I am an active maintainer of the Homebrew package manager for macOS (and Linux). Here are some of my other interests: languages, cricket, tennis, comics (manga and manhwa), music (mostly Carnatic, Indian film, and Asian), theatre, and quizzing.