machine learning for neural decoding

• DOI: 10.48550/arxiv.1708.00909
• Publication Date: 2020-07-01
• Authors: Konrad P. Kording; Konrad P. Kording; Konrad P. Kording; Joshua I. Glaser; Ari S. Benjamin; Matthew G. Perich; Lee E. Miller; Raeed H. Chowdhury
• Keywords: FOS: Computer and information sciences; 0301 basic medicine; Computer Science - Machine Learning; Motor Cortex; 006; Machine Learning (stat.ML); Research Article: Methods/New Tools; Machine Learning (cs.LG); Machine Learning; 03 medical and health sciences; Statistics - Machine Learning; Quantitative Biology - Neurons and Cognition; Brain-Computer Interfaces; FOS: Biological sciences; Neurons and Cognition (q-bio.NC); Neural Networks, Computer; Algorithms

AbstractDespite rapid advances in machine learning tools, the majority of neural decoding approaches still use traditional methods. Modern machine learning tools, which are versatile and easy to use, have the potential to significantly improve decoding performance. This tutorial describes how to effectively apply these algorithms for typical decoding problems. We provide descriptions, best practices, and code for applying common machine learning methods, including neural networks and gradient boosting. We also provide detailed comparisons of the performance of various methods at the task of decoding spiking activity in motor cortex, somatosensory cortex, and hippocampus. Modern methods, particularly neural networks and ensembles, significantly outperform traditional approaches, such as Wiener and Kalman filters. Improving the performance of neural decoding algorithms allows neuroscientists to better understand the information contained in a neural population and can help to advance engineering applications such as brain–machine interfaces. Our code package is available atgithub.com/kordinglab/neural_decoding.