In this post we get to see an example of self-organizing map (or SOM) and also see competitive learning in action. This is where one neuron wins at each presentation of input data, and in this way we are able to map a few neurons to large and complex data. The importance of this mapping is that we are able to extract key features of highly complex data in a completely autonomous way.
The video below explains the various components at a high level. If I can explain something better – please let me know using the comment section below!
If you have any suggestions on how I can improve this page, please let me know.