In a U-Matrix, black cells indicate data items that are similar to each other and white cells indicate borders between groups of similar items. The demo uses the SOM to create what's called a U-Matrix, shown in Figure 1. The demo begins by creating a 30 x 30 SOM for the well-known Fisher's Iris dataset. Take a look at a demo program in Figures 1 and 2. If you have data with class labels, a SOM can be used for dimensionality reduction so the data can be graphed, where the resulting graph indicates how similar different classes are. If you have data without class labels, a SOM can indicate how many classes there are in the data. Briefly, a SOM is a data structure that allows you to investigate the structure of a set of data. A self-organizing map (SOM) is a bit hard to describe.
0 Comments
Leave a Reply. |