Measuring and modeling the motor system with machine learning. (October 2021)

• Record Type: Journal Article
• Authors: Hausmann, Sebastien B.; Vargas, Alessandro Marin; Mathis, Alexander; Mathis, Mackenzie W.
• Is Part Of: Current opinion in neurobiology. Volume 70(2021)
• Page Start: 11
• Page End: 23
• Publication Date: 2021-10
• Subjects: Neurobiology -- Periodicals; 573.8
• DOI: 10.1016/j.conb.2021.04.004
• Languages: English
• ISSNs: 0959-4388

Abstract

Abstract: The utility of machine learning in understanding the motor system is promising a revolution in how to collect, measure, and analyze data. The field of movement science already elegantly incorporates theory and engineering principles to guide experimental work, and in this review we discuss the growing use of machine learning: from pose estimation, kinematic analyses, dimensionality reduction, and closed-loop feedback, to its use in understanding neural correlates and untangling sensorimotor systems. We also give our perspective on new avenues, where markerless motion capture combined with biomechanical modeling and neural networks could be a new platform for hypothesis-driven research. Highlights: Deep learning–based tools allow for robust automation of movement capture and analysis. New approaches to modeling the sensorimotor system enable new hypotheses to be generated. These tools are poised to transform our ability to study the motor system.