Computational Neuroscience: NeuroAI and Geometric Data Analysis

We develop mathematical theories to decipher how neurons collectively give rise to behavior in biological and artificial neural networks.

Visit the Lab Website

About

Our focus lies at the intersection of computational neuroscience and deep learning.

By developing novel mathematical theories, we aim to:

analyze the geometries that underly neural or feature representations, embedding and transferring information
build neural network models and learning rules guided by neuroscience

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 test ideas on neural data, which often lead to further inspiration and idea development.