Alexander Mathis Group of Computational Neuroscience & AI

Broadly speaking, we work at the intersection of computational neuroscience and machine learning. Ultimately, we are interested in reverse engineering the algorithms of the brain, in order to figure out how the brain works and to build better artificial intelligence systems.

Research focus

Machine Learning Tools for Animal Behavior Analysis

See more

Neural Network Modeling of Sensorimotor Representations

See more

DeepLabCut-Live! real-time marker-less motion capture for animals

See more
Lymphomoid spiral (created by Albert Santamaria-Martinez).

New cancer models could help personalize lymphoma treatments

— Scientists at EPFL have developed "lymphomoids," a pioneering cancer model that preserves the structure and multicellular composition of lymphoma tumors in the lab. Lymphomoids offer an innovative way to test the efficacy of lymphoma treatments and better predict individual responses.

Digitally generated cell representation © iStock

AI-Powered Virtual Cell Could Become Biology's Universal Simulator

— More than 40 researchers from across the fields of AI and biology, including from EPFL, have set out their vision for AI-powered Virtual Cells, arguing that these have the potential to revolutionize the scientific process.

Friedhelm Hummel. Credit: EPFL

Friedhelm Hummel awarded Fürst Donnersmarck Prize

— Friedhelm Hummel, head of EPFL's Hummel Lab and a core member of the NeuroX Institute, has been recognized for his groundbreaking research in neurorehabilitation with the Fürst Donnersmarck Prize.