Cooperative information control for self-organization maps

This paper proposes a novel information theoretic approach to self-organization, called cooperative information control. The method aims to mediate between competition and cooperation among neurons by controlling the information content in neurons. Competition is realized by maximizing the information content in neurons. In the process of information maximization, only a small number of neurons win the competition, while all the others are inactive. Cooperation is implemented by having neurons behave similarly to their neighbors. These two processes are unified and controlled in the framework of cooperative information control. We applied the new method to linguistic analyses. In the analyses, experimental results confirmed that competition and cooperation are flexibly controlled. In addition, controlled processes can yield a number of different neuron firing patterns, which can be used to detect macro as well as micro features in input patterns