Convolutional Self Organizing Map
Hiroshi Dozono, Gen Niina, Satoru Araki · 2016
Recently, deep learning became very popular, and was applied to many fields. The convolutional neural networks are often used for representing the layers for deep learning. In this paper, we propose Convolutional Self Organizing Map, which can be applicable to deep learning. Conventional Self Organizing Map uses single layered architecture, and can visualizes and classifies the input data on 2 dimensional map. SOMs which uses multiple layers are already proposed. In this paper, we propose Self Organizing Map algorithms which include convolutional layers. 2 types of convolution methods, which are based on conventional method and inspired from Self Organizing Map algorithm are proposed, and the performance of both method is examined in the experiments of clustering image data.