CHAOSOM: Collaboration between Chaos and Self-Organizing Map
Haruna Matsushita, Yoshifumi Nishio · 2006
In this study, we try to implant chaotic features into the learn-ing algorithm of self-organizing map. We call this concept as Chaotic SOM (CHAOSOM). As a first step to realize CHAO-SOM, we consider the case that learning rate and neighboring coefficient of SOM are refreshed by chaotic pulses generated by the Hodgkin-Huxley equation. We apply the CHAOSOM to solve a traveling salesman problem and confirm that the chaotic feature improves the performance.