%0 Conference Paper
%A Raimondo, Federico
%A Antonopoulos, Georgios
%A Eickhoff, Simon
%A Patil, Kaustubh
%T FASTGPR: DIVIDE-AND-CONQUER TECHNIQUE IN NEUROIMAGING DATA SHORTENS TRAINING TIME AND IMPROVES ACCURACY
%M FZJ-2024-07621
%D 2024
%X Gaussian process regression (GPR) has shown great potential for studying healthy aging and disease via brain-age prediction (BAP) using structural MRI[1].A big drawback of GPR is the training complexity which is an O(N^3) operation (N=number of data points).The need for expansive datasets and the high dimensionality of MRI data, renders the training of GPR impractical with conventional computing resources.We investigated whether a divide-and-conquer approach can be used together with the GPR model
%B International Symposium of Biomedical Imaging 2024
%C 27 May 2024 - 30 May 2024, Athens (Greece)
Y2 27 May 2024 - 30 May 2024
M2 Athens, Greece
%F PUB:(DE-HGF)24
%9 Poster
%R 10.34734/FZJ-2024-07621
%U https://juser.fz-juelich.de/record/1034875