Open Positions:
We are always actively looking for Undergraduate and Master’s students with interests in Behavioral Analysis & Modeling Sensorimotor Learning. We are also regularly recruiting PhD students. If you want to join the lab as a postdoctoral fellow, please check out the following programs: SNSF Swiss Postdoctoral Fellowship, and the EPFL AI Center Postdoctoral Fellowship.
Our Research Themes:
1) Machine Learning Tools for Animal Behavior Analysis - We strive to develop computer vision and machine learning tools for the analysis and quantification of animal behavior. Published work in this field includes DeepLabCut, a popular open-source software tool for pose estimation. For action segmentation, check out DLC2action, AmadeusGPT, hBehaveMAE as well as WildCLIP. Let us know if you are interested in those topics!
2) Modeling of Sensorimotor Learning - We develop normative theories of neural systems that are trained to perform sensorimotor behaviors as well as task-driven models (e.g., DeepDraw, Task-driven-Proprioception, DMAP and Lattice). Furthermore, we will compare and contrast those with data from mice, and primates incl. humans performing motor skills.
We are passionate about open-source code. Check out our group’s GitHub page!
We are looking for motivated individuals with a background in mathematics, computer science, computational neuroscience and related fields.
Lab Immersions, Master projects for EPFL students, please email Alexander (alexander.mathis@epfl.ch) your research interests and CV. Some projects ideas are listed here.
PhD candidates should apply directly to the Doctoral Program in Neuroscience or the Doctoral program in computer and communication sciences at EPFL. Feel free to reach out if you have questions about potential projects.
Postdoctoral Fellows: Please send Alexander (alexander.mathis@epfl.ch) your research interests and CV.
Recommended reading for Machine Learning Tools for Animal Behavior Analysis:
Deep learning tools for the measurement of animal behavior in neuroscience by M.W. Mathis and A. Mathis Current Opinion in Neurobiology, 2020
A Primer on Motion Capture with Deep Learning: Principles, Pitfalls and Perspectives by A. Mathis, S. Schneider, J. Lauer & M.W. Mathis; Neuron, 2020
DeepLabCut: markerless pose estimation of user-defined body parts with deep learning by A. Mathis et al. Nature Neuroscience, 2018
Multi-animal pose estimation, identification and tracking with DeepLabCut by J. Lauer, M. Zhou, S. Ye, … , C. Dulac, M.W. Mathis*, A. Mathis*. Nature Methods, 2022
Toward a science of computational ethology by DJ. Anderson and P. Perona, Neuron, 2014
Recommended reading for Modeling of Sensorimotor Circuits:
DMAP: a Distributed Morphological Attention Policy for Learning to Locomote with a Changing Body by A.S. Chiappa, A. Marin Vargas, A. Mathis. NeurIPS, 2022.
Acquiring musculoskeletal skills with curriculum-based reinforcement learning by A.S. Chiappa, P. Tano, N. Patel, A. Ingster, A. Pouget, A. Mathis bioRxiv, 2024.01. 24.577123
Measuring and modeling the motor system with machine learning by S.B. Hausmann, A.M. Vargas, A Mathis, M.W. Mathis Current Opinion in Neurobiology, 2021
Using goal-driven deep learning models to understand sensory cortex by D.L. Yamins and J. J DiCarlo Nat. Neurosci., 2016
Somatosensory cortex plays an essential role in forelimb motor adaptation in mice. by M.W. Mathis, A. Mathis, and N. Uchida Neuron, 2017