Prof Alexander Mathis Group

The Alexander Mathis Group of Computational Neuroscience & AI at EPFL focuses on reverse engineering the algorithms of the brain to understand its functioning and develop better artificial intelligence systems. Their research includes developing machine learning tools for animal behavior analysis and neural network modeling of sensorimotor representations. They have published work on task-driven neural network models predicting neural dynamics, contrasting action and posture coding, and exploring the role of striatal dopamine in behavioral dynamics. The group also works on student projects related to machine learning tools for animal behavior analysis and modeling of sensorimotor learning and control.

Graph Chatbot

Task-driven neural network models predict neural dynamics of proprioception: Neural network model weights

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Safe Deep Neural Networks

Task-driven neural network models predict neural dynamics of proprioception: Neural network model weights

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Safe Deep Neural Networks