Skip to main content

Simultaneus prediction of four kinematic variables for a brain-machine interface using a single recurrent neural network.

Publication ,  Journal Article
Sanchez, JC; Principe, JC; Carmena, JM; Lebedev, MA; Nicolelis, MAL
Published in: Conf Proc IEEE Eng Med Biol Soc
2004

Implementation of brain-machine interface neural-to-motor mapping algorithms in low-power, portable digital signal processors (DSPs) requires efficient use of model resources especially when predicting signals that show interdependencies. We show here that a single recurrent neural network can simultaneously predict hand position and velocity from the same ensemble of cells using a minimalist topology. Analysis of the trained topology showed that the model learns to concurrently represent multiple kinematic parameters in a single state variable. We further assess the expressive power of the state variables for both large and small topologies.

Duke Scholars

Published In

Conf Proc IEEE Eng Med Biol Soc

DOI

ISSN

1557-170X

Publication Date

2004

Volume

2004

Start / End Page

5321 / 5324

Location

United States
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Sanchez, J. C., Principe, J. C., Carmena, J. M., Lebedev, M. A., & Nicolelis, M. A. L. (2004). Simultaneus prediction of four kinematic variables for a brain-machine interface using a single recurrent neural network. Conf Proc IEEE Eng Med Biol Soc, 2004, 5321–5324. https://doi.org/10.1109/IEMBS.2004.1404486
Sanchez, J. C., J. C. Principe, J. M. Carmena, Mikhail A. Lebedev, and M. A. L. Nicolelis. “Simultaneus prediction of four kinematic variables for a brain-machine interface using a single recurrent neural network.Conf Proc IEEE Eng Med Biol Soc 2004 (2004): 5321–24. https://doi.org/10.1109/IEMBS.2004.1404486.
Sanchez JC, Principe JC, Carmena JM, Lebedev MA, Nicolelis MAL. Simultaneus prediction of four kinematic variables for a brain-machine interface using a single recurrent neural network. Conf Proc IEEE Eng Med Biol Soc. 2004;2004:5321–4.
Sanchez, J. C., et al. “Simultaneus prediction of four kinematic variables for a brain-machine interface using a single recurrent neural network.Conf Proc IEEE Eng Med Biol Soc, vol. 2004, 2004, pp. 5321–24. Pubmed, doi:10.1109/IEMBS.2004.1404486.
Sanchez JC, Principe JC, Carmena JM, Lebedev MA, Nicolelis MAL. Simultaneus prediction of four kinematic variables for a brain-machine interface using a single recurrent neural network. Conf Proc IEEE Eng Med Biol Soc. 2004;2004:5321–5324.

Published In

Conf Proc IEEE Eng Med Biol Soc

DOI

ISSN

1557-170X

Publication Date

2004

Volume

2004

Start / End Page

5321 / 5324

Location

United States