The NeuroAI and Geometric Data Analysis Lab is located in the Department of Physics and the Center for Brain Science at Harvard University, and at the Kempner Institute for the Study of Natural and Artificial Intelligence. We also maintain a partial presence at the Center for Computational Neuroscience at the Flatiron Institute, an internal research division of the Simons Foundation focused on computation. Our lab seeks to develop mathematical theories for understanding how structure gives rise to function in biological and artificial neural networks. We focus on addressing this question through two broad approaches at the intersection of deep learning and brain science:
To do this, we combine computational tools from theoretical physics, applied math, and machine learning. Alongside this theoretical work, we develop close collaborations with experimentalists to be inspired by and to test ideas on neural data.