Collage of multiple colour fields.

Posted: April 22, 2016 at 5:05 pm

The following image is constructed by taking a single row from each of the trained networks such that the lowest (bottom) row has the smallest neighbourhood size (1) and the highest (top) row has the largest (170). Note that very little of the image is readable because the image is abstracted very quickly as the neighbourhood size increases in steps of 1. Note some stability in structure (position of colours) near the bottom of the image. Near the top the increasing horizontality indicates large differences in structure in subsequent neighbourhood sizes.

genSOMVizCVBatch-sigma1-170

The default neighbourhood size (calculated by ANNetGPGPU for this network) is around 390. If the top row corresponded to this neighbourhood size the original image would be even less readable. To make more of the original image readable, the neighbourhood sizes should increase by steps smaller than 1, or multiple rows should show the results of the same network.