Skip to main content
. 2020 Apr 22;41(12):3235–3252. doi: 10.1002/hbm.25011

FIGURE 1.

FIGURE 1

Network architecture for age prediction. (a) The detailed architecture of the network used for age prediction from 3D T1 MRI volume. BatchNorm = batch normalization, Conv = convolutional layer, ReLU = rectified linear unit, FC = fully connected layer. (b) The ensemble procedure combining the output of 10 separately trained CNNs (Γ1–10) using linear regression to create the final age prediction