Parallel Process Neural Networks and Its Application in the Predication of Sunspot Number Series

To address the problem of approximation and prediction of complex time-varying system, this paper proposes a parallel process neural networks predication method based on general process neural networks models. Firstly, the whole time-varying process is divided into several small time intervals; then, the process neural networks are constructed respectively in the small time intervals to disperse the load of networks. According to the theory of orthogonal function basis expansion in functional space, the learning algorithm of the above model is deduced; finally, the results of time series predication for sunspots shows that the proposed method can balance the load of networks and improve the approximation and prediction ability of networks.