Reliability of dissimilarity measures for multi-voxel pattern analysis
详细信息 查看全文
- 作者：Alexander Walthera ; b ; alexander.walther@mrc-cbu.cam.ac.uk" class="auth_mail" title="E-mail the corresponding author ; Hamed Nilic ; hamed.nili@psy.ox.ac.uk" class="auth_mail" title="E-mail the corresponding author ; Naveed Ejazb ; n.ejaz@ucl.ac.uk" class="auth_mail" title="E-mail the corresponding author ; Arjen Alinka ; arjen.alink@mrc-cbu.cam.ac.uk" class="auth_mail" title="E-mail the corresponding author ; Nikolaus Kriegeskortea ; nikolaus.kriegeskorte@mrc-cbu.cam.ac.uk" class="auth_mail" title="E-mail the corresponding author ; Jö ; rn Diedrichsenb ; j.diedrichsen@ucl.ac.uk" class="auth_mail" title="E-mail the corresponding author
- 关键词：fMRI ; Multi-voxel pattern analysis ; Representational similarity analysis ; Crossvalidation ; Linear discriminant ; Noise normalization ; Classification ; Decoding ; Machine learning
- 刊名：NeuroImage
- 出版年：2016
- 出版时间：15 August 2016
- 年：2016
- 卷：137
- 期：Complete
- 页码：188-200
- 全文大小：1081 K
文摘
- class="listitem" id="list_l0005">
- class="label">•
We compare the reliability of dissimilarity measures and classifiers in fMRI.
- class="label">•
We examine the effect of noise normalizations and crossvalidation on reliability.
- class="label">•
Multivariate noise normalization makes the dissimilarity measures more reliable.
- class="label">•
Crossvalidation makes the dissimilarity measures more reliable and unbiased.
- class="label">•
Dissimilarities measure brain representations more reliably than classifiers.