English: CNN reduced dataset. The crosses are the class-outliers selected by 3NN (i.e. (3,1)NN rule: among three nearest neighbours they have more than 1 instance of different classes), the squares are the prototypes and the empty circles are the absorbed points. In the lebt bottom corner the numbers of the class-outliers, prototypes and absorbed poitns are shown for all three classes. My own work done with the software E. M. Mirkes, KNN and Potential Energy: applet. University of Leicester, 2011. Published under Attribution 3.0 Unported (CC BY 3.0) licence.