Research on the improvement for RBF neural networks based on cloud theory

Based on cloud theory, an improved algorithm on RBF neural networks is presented with replaced Gauss radial basic function by normal cloud model, and verification was put in effect with fouling data. The conclusion shows that the improved algorithm is superior to the classical RBF in prediction and the actual result is well. Simultaneously, the improved algorithm can be transplanted to the improvement of RBF neural networks algorithms.