Interpreting spatial and temporal neural activity through a recurrent neural network brain-machine interface

Justin C. Sanchez; Deniz Erdogmus; Miguel A L Nicolelis; Johan Wessberg; Jose C. Principe

doi:10.1109/TNSRE.2005.847382

Interpreting spatial and temporal neural activity through a recurrent neural network brain-machine interface

Justin C. Sanchez, Deniz Erdogmus, Miguel A L Nicolelis, Johan Wessberg, Jose C. Principe

Research output: Contribution to journal › Article

33 Scopus citations

Abstract

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.

Original language	English
Pages (from-to)	213-219
Number of pages	7
Journal	IEEE Transactions on Neural Systems and Rehabilitation Engineering
Volume	13
Issue number	2
DOIs	https://doi.org/10.1109/TNSRE.2005.847382
State	Published - Jun 1 2005
Externally published	Yes

Fingerprint

Keywords

Analysis of neural activity
Brain-machine interface (BMI)
Motor systems
Nonlinear models
Recurrent neural network
Spatio-temporal

ASJC Scopus subject areas

Rehabilitation
Biophysics
Bioengineering
Health Professions(all)

Cite this

Sanchez, J. C., Erdogmus, D., Nicolelis, M. A. L., Wessberg, J., & Principe, J. C. (2005). Interpreting spatial and temporal neural activity through a recurrent neural network brain-machine interface. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 13(2), 213-219. https://doi.org/10.1109/TNSRE.2005.847382

Interpreting spatial and temporal neural activity through a recurrent neural network brain-machine interface. / Sanchez, Justin C.; Erdogmus, Deniz; Nicolelis, Miguel A L; Wessberg, Johan; Principe, Jose C.

In: IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol. 13, No. 2, 01.06.2005, p. 213-219.

Research output: Contribution to journal › Article

@article{b5683f34869e4b7ab5c14047f4a07d59,

title = "Interpreting spatial and temporal neural activity through a recurrent neural network brain-machine interface",

abstract = "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.",

keywords = "Analysis of neural activity, Brain-machine interface (BMI), Motor systems, Nonlinear models, Recurrent neural network, Spatio-temporal",

author = "Sanchez, {Justin C.} and Deniz Erdogmus and Nicolelis, {Miguel A L} and Johan Wessberg and Principe, {Jose C.}",

year = "2005",

month = jun

day = "1",

doi = "10.1109/TNSRE.2005.847382",

language = "English",

volume = "13",

pages = "213--219",

journal = "IEEE Transactions on Neural Systems and Rehabilitation Engineering",

issn = "1534-4320",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "2",

}

TY - JOUR

T1 - Interpreting spatial and temporal neural activity through a recurrent neural network brain-machine interface

AU - Sanchez, Justin C.

AU - Erdogmus, Deniz

AU - Nicolelis, Miguel A L

AU - Wessberg, Johan

AU - Principe, Jose C.

PY - 2005/6/1

Y1 - 2005/6/1

N2 - 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.

AB - 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.

KW - Analysis of neural activity

KW - Brain-machine interface (BMI)

KW - Motor systems

KW - Nonlinear models

KW - Recurrent neural network

KW - Spatio-temporal

UR - http://www.scopus.com/inward/record.url?scp=22544468547&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=22544468547&partnerID=8YFLogxK

U2 - 10.1109/TNSRE.2005.847382

DO - 10.1109/TNSRE.2005.847382

M3 - Article

C2 - 16003902

AN - SCOPUS:22544468547

VL - 13

SP - 213

EP - 219

JO - IEEE Transactions on Neural Systems and Rehabilitation Engineering

JF - IEEE Transactions on Neural Systems and Rehabilitation Engineering

SN - 1534-4320

IS - 2

ER -

Access to Document

10.1109/TNSRE.2005.847382