Generalization of the Self-Organizing Map: From Artificial Neural Networks to Artificial Cortexes
抄録
This paper presents a generalized framework of a self-organizing map(SOM) applicable to more extended data classes rather than vector data. A modularstructure is adopted to realize such generalization; thus, it is called a modularnetwork SOM (mnSOM), in which each reference vector unit of a conventionalSOM is replaced by a functional module. Since users can choose the functionalmodule from any trainable architecture such as neural networks, the mnSOM hasa lot of flexibility as well as high data processing ability. In this paper, the essentialidea is first introduced and then its theory is described.
収録刊行物
-
- Lecture Notes in Computer Science
-
Lecture Notes in Computer Science 4232 943-949, 2006
Springer Berlin / Heidelberg