Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Machine learning for neural decoding

Glaser, Joshua I and Benjamin, Ari S and Chowdhury, Raeed H and Perich, Matthew G and Miller, Lee E and Kording, Konrad P Machine learning for neural decoding.

Submitted Version
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (5MB) | Preview
[img] Plain Text (licence)
Download (1kB)


Despite 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 advance engineering applications such as brain machine interfaces.


Social Networking:
Share |


Item Type: Article
CreatorsEmailPitt UsernameORCID
Glaser, Joshua I
Benjamin, Ari S
Chowdhury, Raeed Hraeed.chowdhury@pitt.eduRAC2170000-0002-5934-919X
Perich, Matthew G
Miller, Lee E
Kording, Konrad P
Schools and Programs: Swanson School of Engineering > Bioengineering
Refereed: Yes
Uncontrolled Keywords: q-bio.NC, q-bio.NC, cs.LG, stat.ML
Date Deposited: 31 Jan 2023 20:11
Last Modified: 02 Feb 2023 06:55


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item