Fig. 2
From: CLeaR: An adaptive continual learning framework for regression tasks
Distributions of the input and the output change over time. We split 10000 samples into four sections sequentially over time, each of which has 2500 samples, and visualize their two-dimensional distributions from (a) to (d). (e) illustrates the distribution of the same 10000 samples. Both axes in the sub-figures, X1 and Y, indicate the first principal component extracted from seven-dimensional weather features using PCA and the power value, respectively