The paper proposes a method of training rough RBF neural networks (R-RBF) using the extreme learning machine (ELM)

which converts the traditional iterative training method to solve norm least-squares solution of general linear system by introducing Moore-Penrose inverse.Experiments show that it can reach a very superior performance in both time and accuracy when ELM trains the Rough RBF Neural Networks

which can improve the generalization accuracy more than 50% compared with the traditional thinking of adjusting parameters iteratively.