Dynamic Feature Extraction by Greedy Information Acquisition Algorithm

R. Kamimura and T. Kamimura (Japan)


Information Maximization, Competitive Learning, Greedy Information Acquisition


In this paper, we propose a new information theoretic approach to competitive learning. The new approach is called greedy information acquisition, because networks try to absorb as much information as possible in every stage of learning. In the first phase, with 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 greedy 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. We also compared our method with the multivariate analysis. The experimental results confirmed that our new method could detect salient features in input patterns more clearly than the other methods.

Important Links:

Go Back