抄録
BP Learning is widely known to perform good classification for given training data. However, when there is a kind of noise or inconsistency of knowledge in training cases, a neural network may fail to converge. To avoid such a problem, we propose an adaptive evolutional neuro learning method to handle a subset of the complete set of training cases. This method has a sufficient adaptive ability similar to a living organism's evolutionary process based on Darwinian Genetic Inheritance. In this method, the network structure is determined by genetic search in each generation and the connection weights and learning parameters determined by BP learning are not inherited. To verify the validity and effectiveness of the proposed method, we developed a diagnostic system for hepatobiliary disorders.
