Mackenzie Weygandt Mathis
Papers
1
Total Citations
8
H-Index
1
About
Mackenzie Weygandt Mathis is a leading figure in computational ethology and AI-driven behavioral neuroscience. Her research centers on developing cutting-edge machine learning tools to quantify animal behavior, with a major focus on pose estimation and motion tracking in freely moving animals. She is best known for co-creating DeepLabCut, a revolutionary deep-learning framework that enables markerless pose estimation with unprecedented accuracy—a tool that has transformed how researchers study movement across species, from rodents to cheetahs. Her work on the AcinoSet dataset, a benchmark for 3D pose estimation in cheetahs, exemplifies her commitment to bridging ecology and robotics, providing baseline models that advance both biological understanding and legged robot design. With over 8,000 citations across her publications, Mathis’s contributions have had a profound impact, earning her recognition such as the NIH Director’s Early Independence Award and the MIT Technology Review Innovators Under 35 honor. Her interdisciplinary approach—merging computer vision, neuroscience, and biomechanics—continues to inspire new generations of scientists to explore the complexities of animal motion and its applications in AI.
Research Focus
Key Achievements
Top Papers
- 1