Measuring and modeling the motor system with machine learning
arXiv:2103.11775 · doi:10.1016/j.conb.2021.04.004
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.
References in corpus (16)
- Scikit-learn: Machine Learning in Python
- Auto-Encoding Variational Bayes
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- Variational Inference: A Review for Statisticians
- Learning Quadrupedal Locomotion over Challenging Terrain
- Emergence of Locomotion Behaviours in Rich Environments
- Solving Rubik's Cube with a Robot Hand
- Deep learning tools for the measurement of animal behavior in neuroscience
- Artificial neural networks for neuroscientists: A primer
- WILDS: A Benchmark of in-the-Wild Distribution Shifts
- A Primer on Motion Capture with Deep Learning: Principles, Pitfalls and Perspectives
- Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control
- Natural Adversarial Examples
- Self-supervised learning through the eyes of a child
- Efficient and Robust Reinforcement Learning with Uncertainty-based Value Expansion
- Deep Reinforcement Learning for Neural Control
Cited by in corpus (5)
- SuperAnimal pretrained pose estimation models for behavioral analysis
- AcinoSet: A 3D Pose Estimation Dataset and Baseline Models for Cheetahs in the Wild
- Parallel locomotor control strategies in mice and flies
- Machine Learning in Biomechanics: Key Applications and Limitations in Walking, Running, and Sports Movements
- Adaptive Intelligence: leveraging insights from adaptive behavior in animals to build flexible AI systems