In this paper, we propose a new information theoretic approach to competitive learning. The new approach is called repeated information maximization. This method maximizes information repeatedly by recruiting a new competitive unit. In the first phase, with a minimum network architecture for realizing competition, information is maximized. In the second phase, a new unit is added, and thereby information is again increased as much as possible. This process continues until no more increase in information is possible. Through repeated information maximization, different sets of important features in input patterns can be cumulatively discovered in successive stages. We applied our approach to a phonological feature detection problem. Experimental results confirmed that information maximization can be repeatedly applied and that different features in input patterns are gradually discovered.
展开▼
