Extraction method of rules from reflective neural network architecture
Takumi Ichimura, N. Matsumoto, E. Tazaki, Kunihiro Yoshida · Proceedings of International Conference on Neural Networks (ICNN'97) · 2002
Reflective neural network is a new architecture with a learning procedure for systems composed of many networks based on a network module concept. To learn a subset of the complete set of training data, each module has two kinds of feedforward networks; a monitor network and a worker network. A monitor network estimates how good a worker network is for distributed training data. We propose an extraction method of fuzzy rules from the modified network based on the reflective neural network. To verify the validity and the effectiveness of the proposed method, we develop a medical diagnostic system for thyroid diseases.