Hierarchy supervised som SOM neural network applied for classification problem
Le Anh Tu, Nguyen Quang Hoan, Le Son Thai · Journal of Computer Science and Cybernetics · 2014
In this paper, supervised SOM neural network was suggested, with S-SOM and S-SOM + applied for classification problems.These networks were developed from supervised and unsupervised SOM model by Kohonen and other researchers.Hierarchy supervised SOM models were developed from the S-SOM and S-SOM + , called HS-SOM and HS-SOM + .Our improvement was inspired by the idea of finding neurons that wrongly classify samples, which created extra training branches for the representative samples of these neurons.Experiments on 11 single-label classification datasets were executed.The results showed that the suggested model classified samples with high accuracy, from 92% to 100%.