Representing acquired knowledge of neural networks by fuzzy sets: control of internal information of neural networks by entropy minimization
Ryotaro Kamimura, Ronald R. Yager, S. Nakanishi · 1994
The authors propose an entropy algorithm to extract the internal information of the neural networks, and show that the extracted information is expressed by fuzzy sets. Fuzzy sets representing internal information of neural networks after learning are composed of the competitive hidden unit activities which can be controlled by the entropy method. We apply this method to meaning interpretation of alphabet.>