Nonlinear Spring Model of Self-Organizing Map and its Chaotic Behavior
The Self-Organizing Map (SOM) is an unsupervised neural network introduced by Kohonen and is a model simpli-fying self-organization process of the brain. However, SOM is still far away from the realization of the brain mechanism. In order to realize more powerful and more flexible mechanism, it is important to propose new models of the brain mechanism and toinvestigate their behaviors. In this study, as the first step to realize a new nonlinear spring model of SOM, we propose a simple one dimensional 2-neuron model connected by a nonlinear spring. We investigate its behavior under a simple assumption where input vectors are given to the model periodically. Computer simulated results show that the neurons oscillate chaotically.
Haruna MATSUSHITA Yoshifumi NISHIO
Department of Electrical and Electronic Engineering, Tokushima University 2–1 Minami-Josanjima, Tokushima 770–8506, Japan
国际会议
2007年通信、电路与系统国际会议(2007 International Conference on Communications,Circuits and Systems Proceedings)
日本福冈
英文
2007-07-11(万方平台首次上网日期,不代表论文的发表时间)