Interpreting spatial and temporal neural activity through a recurrent neural network brain-machine interface.
Journal Article (Journal Article)
We propose the use of optimized brain-machine interface (BMI) models for interpreting the spatial and temporal neural activity generated in motor tasks. In this study, a nonlinear dynamical neural network is trained to predict the hand position of primates from neural recordings in a reaching task paradigm. We first develop a method to reveal the role attributed by the model to the sampled motor, premotor, and parietal cortices in generating hand movements. Next, using the trained model weights, we derive a temporal sensitivity measure to asses how the model utilized the sampled cortices and neurons in real-time during BMI testing.
Full Text
Duke Authors
Cited Authors
- Sanchez, JC; Erdogmus, D; Nicolelis, MAL; Wessberg, J; Principe, JC
Published Date
- June 2005
Published In
Volume / Issue
- 13 / 2
Start / End Page
- 213 - 219
PubMed ID
- 16003902
Electronic International Standard Serial Number (EISSN)
- 1558-0210
International Standard Serial Number (ISSN)
- 1534-4320
Digital Object Identifier (DOI)
- 10.1109/tnsre.2005.847382
Language
- eng