Model-based feature construction for multivariate decoding.

Model-based feature construction for multivariate decoding.
复制标题

DOI:
10.1016/j.neuroimage.2010.04.036
复制
发表时间:
2011-05-15
期刊:
影响因子:
5.7
通讯作者:
Stephan KE
Stephan KE
中科院分区:
医学1区
文献类型:
--
作者:
Brodersen KH;Haiss F;Ong CS;Jung F;Tittgemeyer M;Buhmann JM;Weber B;Stephan KE

文献摘要

参考文献

被引文献

相似文献

神经科学中的传统解码方法旨在从神经活动的多变量相关性预测离散的大脑状态。这种方法面临两个重要挑战。首先,少量的例子通常由大量的特征表示,这使得很难选择允许准确预测的少数信息特征。其次,准确性估计和信息图通常仍然是描述性的,很难解释。在本文中,我们提出了一种基于模型的解码方法,从一个新的角度来解决这两个挑战。我们的方法包括:(i)以逐个试验的方式反转神经生理数据的动态因果模型;(ii)在从模型参数的试验式估计得到的强烈减少的特征空间上训练和测试判别分类器;以及(iii)重建分离超平面。由于该方法是基于模型的,它提供了一个原则性的特征空间的降维;此外,如果该模型是神经生物学上合理的,解码结果可以提供一个机械意义的解释。所提出的方法可以与各种建模方法和大脑数据结合使用,并支持对试验或受试者标签进行解码。此外,它可以补充基于证据的方法,用于基于模型的解码,并在无法应用贝叶斯模型选择的情况下实现结构模型选择。在这里,我们说明其应用程序使用动态因果模型(DCM)的电生理记录在啮齿动物。我们证明,该方法实现了显着的机会以上的性能,并在同一时间,允许神经生物学的解释的结果。
Conventional decoding methods in neuroscience aim to predict discrete brain states from multivariate correlates of neural activity. This approach faces two important challenges. First, a small number of examples are typically represented by a much larger number of features, making it hard to select the few informative features that allow for accurate predictions. Second, accuracy estimates and information maps often remain descriptive and can be hard to interpret. In this paper, we propose a model-based decoding approach that addresses both challenges from a new angle. Our method involves (i) inverting a dynamic causal model of neurophysiological data in a trial-by-trial fashion; (ii) training and testing a discriminative classifier on a strongly reduced feature space derived from trial-wise estimates of the model parameters; and (iii) reconstructing the separating hyperplane. Since the approach is model-based, it provides a principled dimensionality reduction of the feature space; in addition, if the model is neurobiologically plausible, decoding results may offer a mechanistically meaningful interpretation. The proposed method can be used in conjunction with a variety of modelling approaches and brain data, and supports decoding of either trial or subject labels. Moreover, it can supplement evidence-based approaches for model-based decoding and enable structural model selection in cases where Bayesian model selection cannot be applied. Here, we illustrate its application using dynamic causal modelling (DCM) of electrophysiological recordings in rodents. We demonstrate that the approach achieves significant above-chance performance and, at the same time, allows for a neurobiological interpretation of the results.
DOI: 10.1016/j.neunet.2008.08.007
发表时间: 2008-11-01
期刊: NEURAL NETWORKS
影响因子: 7.8
作者:
Brodersen, Kay H.;Penny, Will D.;Stephan, Klaas E.
通讯作者: Stephan, Klaas E.
DOI: 10.1093/cercor/1.1.1
发表时间: 1991-01-01
期刊: CEREBRAL CORTEX
影响因子: 3.7
作者:
Felleman, Daniel J.;Van Essen, David C.
通讯作者: Van Essen, David C.
DOI: 10.1016/j.neuroimage.2006.08.035
发表时间: 2007-01-01
期刊: NEUROIMAGE
影响因子: 5.7
作者:
Friston, Karl J.;Mattout, Jeremie;Penny, Will
通讯作者: Penny, Will
DOI: 10.1016/j.clinph.2008.11.029
发表时间: 2009-03
期刊: Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology
影响因子: --
作者:
Garrido MI;Kilner JM;Stephan KE;Friston KJ
通讯作者: Friston KJ
DOI: 10.1016/j.neuroimage.2008.11.031
发表时间: 2009-04-01
期刊: NEUROIMAGE
影响因子: 5.7
作者:
Bode, Stefan;Haynes, John-Dylan
通讯作者: Haynes, John-Dylan