We use advanced mathematics to unify the study of intelligence in brains and machines.
We build efficient AI models that succeed where others fail. We deliver up to +66% higher accuracy or the same accuracy with 10× faster models, even when datasets are small, noisy, and complex —such as networks and 3D shapes.
We provide new perspectives in neuroscience, revealing the mathematics that let our brains explore the world, store memories, and master new skills.
Geometric Intelligence Research
Just as physicists uses geometry to build unification theories, we show that brain and machine intelligences can be studied under a common framework: geometric intelligence.
The idea is that data has structure and this structure has power. It helps us redesign the building blocks of AI models to improve their efficiency. It helps us understand how brains compute so effectively.
Geometric Intelligence in Machines
We study the properties of top-performing AI models and design mathematical approaches to improve them. Learn more.
Geometric Intelligence in Brains
We study patterns of neural activity across diverse cognitive functions—from navigation and memory to vision. Learn more.
Building Brain Digital Twins
We use AI models to build digital twins of the brain, simulating its function in both health and disease. Learn more.
Latest News
The Geometric Intelligence Lab Receives a 1.2M$ NSF Grant to Build Vision Systems that Exploit the Symmetries of the Visual World
Led by lab members Christian Shewmake and Sophia Sanborn, the Geometric Intelligence Lab (PI: Nina Miolane) receives a 1.2M$ NSF grant to build deep vision models capable of discove
Read MoreThe Geometric Intelligence Lab Receives a 1.2M$ NSF Grant to Build Vision Systems that Exploit the Symmetries of the Visual World
Sophia Sanborn is on the TWIML AI Podcast with Sam Charrington
Sophia Sanborn, postdoctoral fellow in our Lab, is featured in the renowned TWIML AI Podcast with Sam Charrington.
Watch her discuss why deep networks and brains learn similar features here!
Read MoreSophia Sanborn is on the TWIML AI Podcast with Sam Charrington
Our survey of topological neural networks is the most popular arxiv link!
Our literature review "Architectures of Topological Deep Learning: A Survey of Topological Neural Networks" was the most popular Arxiv link on April 22, 2023!
Congratulations to the authors Mathilde Papillon, Sophia Sanborn and Nina Miolane from our lab, as well as to our collaborator Mustafa Hajij.
Read MoreOur survey of topological neural networks is the most popular arxiv link!