Selecting neural subsets for kinematics decoding by information theoretical analysis in motor Brain Machine Interfaces

Yiwen Wang, Justin C. Sanchez, Jose C. Principe

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Previous decoding algorithms for Brain Machine Interfaces (BMIs) reconstruct the kinematics from recorded activities of hundreds of neurons, which are not all related to the movement task. Decoding from all neurons not only brings problem towards model generalization but also a significant computation burden. Knowledge of neural receptive fields helps ascertain the neuron importance associate with the movements. We propose to apply information theoretical analysis based on an instantaneous tuning model to extract the candidate neuron subsets, which also reduces the computation complexity for the decoding process. The cortical distribution of extracted neuron subsets is analyzed and the statistical decoding performances using neuron subset selection are compared to the one by the full neuron ensemble.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
Pages3275-3280
Number of pages6
DOIs
StatePublished - Nov 18 2009
Externally publishedYes
Event2009 International Joint Conference on Neural Networks, IJCNN 2009 - Atlanta, GA, United States
Duration: Jun 14 2009Jun 19 2009

Other

Other2009 International Joint Conference on Neural Networks, IJCNN 2009
CountryUnited States
CityAtlanta, GA
Period6/14/096/19/09

Fingerprint

Information analysis
Neurons
Decoding
Brain
Kinematics
Set theory
Tuning

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Wang, Y., Sanchez, J. C., & Principe, J. C. (2009). Selecting neural subsets for kinematics decoding by information theoretical analysis in motor Brain Machine Interfaces. In Proceedings of the International Joint Conference on Neural Networks (pp. 3275-3280). [5178809] https://doi.org/10.1109/IJCNN.2009.5178809

Selecting neural subsets for kinematics decoding by information theoretical analysis in motor Brain Machine Interfaces. / Wang, Yiwen; Sanchez, Justin C.; Principe, Jose C.

Proceedings of the International Joint Conference on Neural Networks. 2009. p. 3275-3280 5178809.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Wang, Y, Sanchez, JC & Principe, JC 2009, Selecting neural subsets for kinematics decoding by information theoretical analysis in motor Brain Machine Interfaces. in Proceedings of the International Joint Conference on Neural Networks., 5178809, pp. 3275-3280, 2009 International Joint Conference on Neural Networks, IJCNN 2009, Atlanta, GA, United States, 6/14/09. https://doi.org/10.1109/IJCNN.2009.5178809
Wang Y, Sanchez JC, Principe JC. Selecting neural subsets for kinematics decoding by information theoretical analysis in motor Brain Machine Interfaces. In Proceedings of the International Joint Conference on Neural Networks. 2009. p. 3275-3280. 5178809 https://doi.org/10.1109/IJCNN.2009.5178809
Wang, Yiwen ; Sanchez, Justin C. ; Principe, Jose C. / Selecting neural subsets for kinematics decoding by information theoretical analysis in motor Brain Machine Interfaces. Proceedings of the International Joint Conference on Neural Networks. 2009. pp. 3275-3280
@inproceedings{aca33d806dcc46f487448a3d50169f36,
title = "Selecting neural subsets for kinematics decoding by information theoretical analysis in motor Brain Machine Interfaces",
abstract = "Previous decoding algorithms for Brain Machine Interfaces (BMIs) reconstruct the kinematics from recorded activities of hundreds of neurons, which are not all related to the movement task. Decoding from all neurons not only brings problem towards model generalization but also a significant computation burden. Knowledge of neural receptive fields helps ascertain the neuron importance associate with the movements. We propose to apply information theoretical analysis based on an instantaneous tuning model to extract the candidate neuron subsets, which also reduces the computation complexity for the decoding process. The cortical distribution of extracted neuron subsets is analyzed and the statistical decoding performances using neuron subset selection are compared to the one by the full neuron ensemble.",
author = "Yiwen Wang and Sanchez, {Justin C.} and Principe, {Jose C.}",
year = "2009",
month = "11",
day = "18",
doi = "10.1109/IJCNN.2009.5178809",
language = "English",
isbn = "9781424435531",
pages = "3275--3280",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",

}

TY - GEN

T1 - Selecting neural subsets for kinematics decoding by information theoretical analysis in motor Brain Machine Interfaces

AU - Wang, Yiwen

AU - Sanchez, Justin C.

AU - Principe, Jose C.

PY - 2009/11/18

Y1 - 2009/11/18

N2 - Previous decoding algorithms for Brain Machine Interfaces (BMIs) reconstruct the kinematics from recorded activities of hundreds of neurons, which are not all related to the movement task. Decoding from all neurons not only brings problem towards model generalization but also a significant computation burden. Knowledge of neural receptive fields helps ascertain the neuron importance associate with the movements. We propose to apply information theoretical analysis based on an instantaneous tuning model to extract the candidate neuron subsets, which also reduces the computation complexity for the decoding process. The cortical distribution of extracted neuron subsets is analyzed and the statistical decoding performances using neuron subset selection are compared to the one by the full neuron ensemble.

AB - Previous decoding algorithms for Brain Machine Interfaces (BMIs) reconstruct the kinematics from recorded activities of hundreds of neurons, which are not all related to the movement task. Decoding from all neurons not only brings problem towards model generalization but also a significant computation burden. Knowledge of neural receptive fields helps ascertain the neuron importance associate with the movements. We propose to apply information theoretical analysis based on an instantaneous tuning model to extract the candidate neuron subsets, which also reduces the computation complexity for the decoding process. The cortical distribution of extracted neuron subsets is analyzed and the statistical decoding performances using neuron subset selection are compared to the one by the full neuron ensemble.

UR - http://www.scopus.com/inward/record.url?scp=70449389929&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449389929&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2009.5178809

DO - 10.1109/IJCNN.2009.5178809

M3 - Conference contribution

SN - 9781424435531

SP - 3275

EP - 3280

BT - Proceedings of the International Joint Conference on Neural Networks

ER -