Measuring and modeling the motor system with machine learning
It provides a perspective on integrating machine learning with biomechanical modeling for researchers in movement science, but it is incremental as it reviews existing trends rather than presenting new findings.
This review discusses the application of machine learning techniques, such as pose estimation and neural networks, to enhance data collection and analysis in movement science, aiming to advance hypothesis-driven research in understanding the motor system.
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.