Toward an Improvement of the Analysis of Neural Coding.
Toward an Improvement of the Analysis of Neural Coding.
复制标题
DOI：
10.3389/fninf.2017.00077
复制
发表时间：
2017
影响因子：
3.5
通讯作者：
Fernandez E
中科院分区：
文献类型：
--
作者：
Alegre-Cortés J;Soto-Sánchez C;Albarracín AL;Farfán FD;Val-Calvo M;Ferrandez JM;Fernandez E
机器学习和人工智能在神经计算原理上有很强的根基。一些例子是第一个感知器的结构，灵感来自视网膜，基于神经节细胞记录或Hopfield网络的神经修复术。此外，机器学习提供了一套强大的工具来分析神经数据，这已经在语音识别、行为状态分类或LFP记录等遥远的研究领域证明了其有效性。然而，尽管在过去的几年中，神经数据的降维，模式选择和聚类方面取得了巨大的技术进步，但用于神经科学中的时频（T-F）分析的分析工具并没有成比例的发展。考虑到这一点，我们引入了使用非线性，非平稳工具，特别是EMD算法的便利性，用于将振荡神经数据（EEG，EMG，尖峰振荡......）转换到T-F域，然后再用机器学习工具进行分析。我们支持，为了获得有意义的结论，我们分析的转换数据必须尽可能忠实于原始记录，因此由于T-F计算中的限制而被迫转换到数据中的转换不会扩展到机器学习分析的结果。此外，生物启发计算（例如脑机接口）可以从考虑神经元动力学非线性的神经元编码的更精确定义中得到丰富。
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.
登录
查看更多内容
影响因子：
3
作者：
Alegre-Cortes，J.;Soto-Sanchez，C.;Fernandez，E.
通讯作者：
Fernandez，E.
影响因子：
4.6
作者：
Carlson, David E.;Vogelstein, Joshua T.;Carin, Lawrence
通讯作者：
Carin, Lawrence
影响因子：
2.7
作者：
POWELL, MJD
通讯作者：
POWELL, MJD
DOI：
10.1109/pgec.1965.264137
发表时间：
1965-01-01
期刊：
IEEE TRANSACTIONS ON ELECTRONIC COMPUTERS
影响因子：
--
作者：
COVER, TM
通讯作者：
COVER, TM
影响因子：
8
作者：
Bongard, Markus;Micol, Daniel;Fernandez, Eduardo
通讯作者：
Fernandez, Eduardo