Statistical learning analysis in neuroscience: aiming for transparency
- 1
Center for Cognitive Neuroscience, Dartmouth College, Hanover, NH, USA
- 2
Department of Psychological and Brain Sciences, Dartmouth College, Hanover, NH, USA
- 3
Department of Experimental Psychology, University of Magdeburg, Magdeburg, Germany
- 4
Center for Behavioral Brain Sciences, Magdeburg, Germany
Encouraged by a rise of reciprocal interest between the machine learning and neuroscience communities, several recent studies have demonstrated the explanatory power of statistical learning techniques for the analysis of neural data. In order to facilitate a wider adoption of these methods, neuroscientific research needs to ensure a maximum of transparency to allow for comprehensive evaluation of the employed procedures. We argue that such transparency requires “neuroscience-aware” technology for the performance of multivariate pattern analyses of neural data that can be documented in a comprehensive, yet comprehensible way. Recently, we introduced PyMVPA, a specialized Python framework for machine learning based data analysis that addresses this demand. Here, we review its features and applicability to various neural data modalities.
Keywords:
machine learning, Python, PyMVPA, MVPA
Citation:
Hanke M, Halchenko YO, Haxby JV and Pollmann S (2010) Statistical learning analysis in neuroscience: aiming for transparency. Front. Neurosci. 4,1: 38-43 doi:10.3389/neuro.01.007.2010
Received: 25 September 2009;
Paper pending published: 14 November 2009;
Accepted: 24 November 2009;
Published online: 15 May 2010
Edited by:
Rolf Kötter, Radboud University Nijmegen, Netherlands
Reviewed by:
Stephen C. Strother, Baycrest, Canada; University of Toronto, Canada
Rolf Kötter, Radboud University Nijmegen, Netherlands
Copyright:
© 2010 Hanke, Halchenko, Haxby and Pollmann. This is an open-access publication subject to an exclusive license agreement between the authors and the Frontiers Research Foundation, which permits unrestricted use, distribution, and reproduction in any medium, provided the original authors and source are credited.
*Correspondence:
Michael Hanke & Dr. Yaroslav O. Halchenko, Dartmouth College, Department of Psychological and Brain Sciences, 419 Moore Hall, Hanover, NH, 03755, USA, michael.hanke@gmail.com, yaroslav.o.halchenko@onerussian.com