Measuring and modeling the motor system with machine learning

TL;DR

This paper reviews how machine learning enhances the measurement and modeling of the motor system, covering pose estimation, neural analysis, and potential new research platforms.

Contribution

It provides a comprehensive overview of machine learning applications in movement science and discusses future directions like markerless motion capture and neural network integration.

Findings

Machine learning improves pose estimation and kinematic analysis.

It aids in understanding neural correlates of movement.

Potential for new hypothesis-driven research platforms.

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.