Toward an Improvement of the Analysis of Neural Coding
Por favor, use este identificador para citar o enlazar este ítem:
http://hdl.handle.net/10045/72370
Título: | Toward an Improvement of the Analysis of Neural Coding |
---|---|
Autor/es: | Alegre-Cortés, Javier | Soto Sánchez, Cristina | Albarracín, Ana L. | Farfán, Fernando D. | Val-Calvo, Mikel | Ferrandez, José M. | Fernandez, Eduardo |
Grupo/s de investigación o GITE: | Biotecnología |
Centro, Departamento o Servicio: | Universidad de Alicante. Departamento de Biotecnología |
Palabras clave: | Neuronal coding | Non-linear signals | NA-MEMD | Machine learning classification | Single trial classification |
Área/s de conocimiento: | Biología Celular |
Fecha de publicación: | 10-ene-2018 |
Editor: | Frontiers Media |
Cita bibliográfica: | Alegre-Cortés J, Soto-Sánchez C, Albarracín AL, Farfán FD, Val-Calvo M, Ferrandez JM and Fernandez E (2018) Toward an Improvement of the Analysis of Neural Coding. Front. Neuroinform. 11:77. doi: 10.3389/fninf.2017.00077 |
Resumen: | Machine learning and artificial intelligence have strong roots on principles of neural computation. Some examples are the structure of the first perceptron, inspired in the retina, neuroprosthetics based on ganglion cell recordings or Hopfield networks. In addition, machine learning provides a powerful set of tools to analyze neural data, which has already proved its efficacy in so distant fields of research as speech recognition, behavioral states classification, or LFP recordings. However, despite the huge technological advances in neural data reduction of dimensionality, pattern selection, and clustering during the last years, there has not been a proportional development of the analytical tools used for Time–Frequency (T–F) analysis in neuroscience. Bearing this in mind, we introduce the convenience of using non-linear, non-stationary tools, EMD algorithms in particular, for the transformation of the oscillatory neural data (EEG, EMG, spike oscillations…) into the T–F domain prior to its analysis with machine learning tools. We support that to achieve meaningful conclusions, the transformed data we analyze has to be as faithful as possible to the original recording, so that the transformations forced into the data due to restrictions in the T–F computation are not extended to the results of the machine learning analysis. Moreover, bioinspired computation such as brain–machine interface may be enriched from a more precise definition of neuronal coding where non-linearities of the neuronal dynamics are considered. |
Patrocinador/es: | This work has been supported in part by the Spanish national research program (MAT2015-69967-C3-1), by Research Chair Bidons Egara and by a research grant of the Spanish Blind Organization (ONCE). |
URI: | http://hdl.handle.net/10045/72370 |
ISSN: | 1662-5196 |
DOI: | 10.3389/fninf.2017.00077 |
Idioma: | eng |
Tipo: | info:eu-repo/semantics/article |
Derechos: | © 2018 Alegre-Cortés, Soto-Sánchez, Albarracín, Farfán, Val-Calvo, Ferrandez and Fernandez. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
Revisión científica: | si |
Versión del editor: | http://dx.doi.org/10.3389/fninf.2017.00077 |
Aparece en las colecciones: | INV - GIDBT - Artículos de Revistas |
Archivos en este ítem:
Archivo | Descripción | Tamaño | Formato | |
---|---|---|---|---|
2018_Alegre-Cortes_etal_FrontNeuroinform.pdf | 1,21 MB | Adobe PDF | Abrir Vista previa | |
Este ítem está licenciado bajo Licencia Creative Commons