Self-creating and adaptive learning of RBF networks: Merging soft-competition clustering algorithm with network growth technique

This paper proposes a hybrid learning algorithm of RBF neural networks. The number of hidden neurons is decided by a network growth technique. A membership function is introduced into training center vectors of Gaussian functions. The reciprocal of fuzzy factor, which is increasing during iteration, is considered as the temperature in simulated annealing. This algorithm can not only effectively overcome initial weight sensitive problem and dead-node problem of C-means clustering algorithm, but also dynamically determine the hidden neurons. Experimental results show that the algorithm proposed in this paper is effect.