Hierarchical Gaussian Näıve Bayes Classifier for Multiple-Subject fMRI Data

The Gaussian Näıve Bayes classifier has been successfully applied to classifying cognitive states using fMRI data. However, the classifier can only be trained using data from only one subject, or by pooling the data and assuming that there are no variations across subjects. I propose the hierarchical Gaussian Näıve Bayes classifier, incorporating ideas from the hierarchical Bayesian models to leverage data from multiple subjects. I present results applying the classifier to two fMRI datasets.

[1]  J. Berger.  Statistical Decision Theory and Bayesian Analysis , 1988 .

[2]  Terry M. Peters,et al.  3D statistical neuroanatomical models from 305 MRI volumes , 1993, 1993 IEEE Conference Record Nuclear Science Symposium and Medical Imaging Conference.

[3]  Rich Caruana,et al.  Multitask Learning , 1998, Encyclopedia of Machine Learning and Data Mining.

[4]  Erik D. Reichle,et al.  The Neural Bases of Strategy and Skill in Sentence–Picture Verification , 2000, Cognitive Psychology.

[5]  Alan C. Evans,et al.  A General Statistical Analysis for fMRI Data , 2000, NeuroImage.

[6]  Karl J. Friston,et al.  Classical and Bayesian Inference in Neuroimaging: Theory , 2002, NeuroImage.

[7]  Tom M. Mitchell,et al.  Training fMRI Classifiers to Discriminate Cognitive States across Multiple Subjects , 2003, NIPS.

[8]  Tom M. Mitchell,et al.  Learning to Decode Cognitive States from Brain Images , 2004, Machine Learning.

[9]  F. Tong,et al.  Decoding the visual and subjective contents of the human brain , 2005, Nature Neuroscience.

[10]  Thomas G. Dietterich,et al.  To transfer or not to transfer , 2005, NIPS 2005.

[11]  Ronald R. Coifman,et al.  Local discriminant bases and their applications , 1995, Journal of Mathematical Imaging and Vision.