Dear PRoNTo developers and users,
I would like to ask you a clarification in terms of feature space in PRoNto. A reviewer asked to define the
feature space of SVM analyses performed of connectivity maps, but I was not sure by considering the effect of kernel trick.
Is it right to state that feature space in PRoNTo, where SVM etc are performed, is defined by kernels, whereas input space (not feature space) is defined by the vector constituted by voxel? Or feature space corresponds to original input space by considering the kernel trick?
Thank you for any help!
Benedetta
########################################################################
To unsubscribe from the PRONTO-USERS list, click the following link:
https://www.jiscmail.ac.uk/cgi-bin/webadmin?SUBED1=PRONTO-USERS&A=1
|