Hypercolumn Model: A Combination Model of Hierarchical Self-Organizing Maps and Neocognitron for Image Recognition

摘要

In this paper, a neural network model, the hyperco- lumn model(HCM), which is applicable to general image recognition, is proposed. The HCM is combination model of hierarchical self-organizing maps(HSOM)and neocog- nitron(NC); it resolves the disadvantages of both the HSOM and the NC, and inherits all of the advantages of Both models. The HSOM quantizes and nonlinearly maps An input space into a small dimensional feature map.