Skip to main content
. 2021 May 26;21(11):3708. doi: 10.3390/s21113708

Figure 6.

Figure 6

Visualizing the uncertainty of predictive distribution in regression tasks. (af) show that (1-MR) × 100 training data with MR = [0.0, 0.1, 0.3, 0.5, 0.7, 0.9], respectively, is used to train the SDE-Net, BBP, and the proposed ConvCNPs–SDE-Net.