Published multiple papers on topics such as neural network geometry, representation learning, contrastive self-supervised learning, etc., appearing in journals and conferences like bioRxiv, arXiv, ICML, NeurIPS, among others.
Research Experience
Holds research experience as an Assistant Professor at Harvard University, with affiliations to the Kempner Institute for the Study of Natural and Artificial Intelligence, the Center for Brain Science, and a part-time position at the Center for Computational Neuroscience at the Flatiron Institute.
Background
Assistant Professor of Physics and Applied Mathematics at Harvard University; Institute Investigator at the Kempner Institute for the Study of Natural and Artificial Intelligence; member in the Center for Brain Science; part-time appointment at the Center for Computational Neuroscience at the Flatiron Institute. Research interests lie at the intersection of computational neuroscience and deep learning, focusing on understanding computation in the brain and artificial neural networks by analyzing geometries underlying neural or feature representations, embedding and transferring information, and developing neural network models and learning rules guided by neuroscience.