在一篇期刊文章上看到了一个data distribution的图，但是在解释这幅图的地方没有给出这个数据分布的定义。求解这个data distribution是否是机器学习或者数据挖掘之类的一个一般性概念？是如何定义的？
如下：
Fig. 8 shows the data distribution for this architecture, as can be observed, despite the fact that we had only few data points per module, some data are very similar to some of the data belonging to different classes, which causes some data overlapping among the classes. This is an important factor that must be considered, since in the application for classification it is a great idea to implement a method of data similarity, and determine which classes could be in the same module of the neural network.
如下：
Fig. 8 shows the data distribution for this architecture, as can be observed, despite the fact that we had only few data points per module, some data are very similar to some of the data belonging to different classes, which causes some data overlapping among the classes. This is an important factor that must be considered, since in the application for classification it is a great idea to implement a method of data similarity, and determine which classes could be in the same module of the neural network.
