Novel Sequential Neural Network Learning Algorithm for Function Approximation

【摘要】 A novel sequential neural network learning algorithm for function approximation is presented. The multi-step-ahead output predictor of the stochastic time series is introduced to the growing and pruning network for constructing network structure. And the network parameters are adjusted by the proportional differential filter (PDF) rather than EKF when the network growing criteria are not met. Experimental results show that the proposed algorithm can obtain a more compact network along with a smaller error in mean square sense than other typical sequential learning algorithms.更多还原

【Abstract】 A novel sequential neural network learning algorithm for function approximation is presented. The multi-step-ahead output predictor of the stochastic time series is introduced to the growing and pruning network for constructing network structure. And the network parameters are adjusted by the proportional differential filter (PDF) rather than EKF when the network growing criteria are not met. Experimental results show that the proposed algorithm can obtain a more compact network along with a smaller error in mean square sense than other typical sequential learning algorithms.更多还原