Tags

Type your tag names separated by a space and hit enter

Ascertaining neuron importance by information theoretical analysis in motor Brain-Machine Interfaces.
Neural Netw. 2009 Jul-Aug; 22(5-6):781-90.NN

Abstract

Point process modeling of neural spike recordings has the potential to capture with high specificity the information contained in spike time occurrence. In Brain-Machine Interfaces (BMIs) the neural tuning characteristic assessed from neural spike recordings can distinguish neuron importance in terms of its modulation with the movement task. Consequently, it improves generalization and reduces significantly computation in previous decoding algorithms, where models reconstruct the kinematics from recorded activities of hundreds of neurons. We propose to apply information theoretical analysis based on an instantaneous tuning model to extract the important neuron subsets for point process decoding on BMI. The cortical distribution of extracted neuron subsets is analyzed and the statistical decoding performance using subset selection is studied with respect to different number of neurons and compared to the one by the full neuron ensemble. With much less computation, the extracted importance neurons provide comparable kinematic reconstructions compared to the full neuron ensemble. The performance of the extracted subset is compared to the random selected subset with same number of neurons to further validate the effectiveness of the subset-extraction approach.

Authors+Show Affiliations

Department of Electrical & Computer Engineering, University of Florida, Gainesville, FL, USA. wangyw@cnel.ufl.eduNo affiliation info availableNo affiliation info available

Pub Type(s)

Journal Article
Research Support, U.S. Gov't, Non-P.H.S.

Language

eng

PubMed ID

19615852

Citation

Wang, Yiwen, et al. "Ascertaining Neuron Importance By Information Theoretical Analysis in Motor Brain-Machine Interfaces." Neural Networks : the Official Journal of the International Neural Network Society, vol. 22, no. 5-6, 2009, pp. 781-90.
Wang Y, Principe JC, Sanchez JC. Ascertaining neuron importance by information theoretical analysis in motor Brain-Machine Interfaces. Neural Netw. 2009;22(5-6):781-90.
Wang, Y., Principe, J. C., & Sanchez, J. C. (2009). Ascertaining neuron importance by information theoretical analysis in motor Brain-Machine Interfaces. Neural Networks : the Official Journal of the International Neural Network Society, 22(5-6), 781-90. https://doi.org/10.1016/j.neunet.2009.06.007
Wang Y, Principe JC, Sanchez JC. Ascertaining Neuron Importance By Information Theoretical Analysis in Motor Brain-Machine Interfaces. Neural Netw. 2009 Jul-Aug;22(5-6):781-90. PubMed PMID: 19615852.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Ascertaining neuron importance by information theoretical analysis in motor Brain-Machine Interfaces. AU - Wang,Yiwen, AU - Principe,Jose C, AU - Sanchez,Justin C, Y1 - 2009/06/30/ PY - 2009/06/07/received PY - 2009/06/25/accepted PY - 2009/7/21/entrez PY - 2009/7/21/pubmed PY - 2009/11/3/medline SP - 781 EP - 90 JF - Neural networks : the official journal of the International Neural Network Society JO - Neural Netw VL - 22 IS - 5-6 N2 - Point process modeling of neural spike recordings has the potential to capture with high specificity the information contained in spike time occurrence. In Brain-Machine Interfaces (BMIs) the neural tuning characteristic assessed from neural spike recordings can distinguish neuron importance in terms of its modulation with the movement task. Consequently, it improves generalization and reduces significantly computation in previous decoding algorithms, where models reconstruct the kinematics from recorded activities of hundreds of neurons. We propose to apply information theoretical analysis based on an instantaneous tuning model to extract the important neuron subsets for point process decoding on BMI. The cortical distribution of extracted neuron subsets is analyzed and the statistical decoding performance using subset selection is studied with respect to different number of neurons and compared to the one by the full neuron ensemble. With much less computation, the extracted importance neurons provide comparable kinematic reconstructions compared to the full neuron ensemble. The performance of the extracted subset is compared to the random selected subset with same number of neurons to further validate the effectiveness of the subset-extraction approach. SN - 1879-2782 UR - https://www.unboundmedicine.com/medline/citation/19615852/Ascertaining_neuron_importance_by_information_theoretical_analysis_in_motor_Brain_Machine_Interfaces_ L2 - https://linkinghub.elsevier.com/retrieve/pii/S0893-6080(09)00110-5 DB - PRIME DP - Unbound Medicine ER -