点击次数：

论文类型：期刊论文

发表时间：2011-01-01

发表刊物：INTERNATIONAL JOURNAL OF NUMERICAL ANALYSIS AND MODELING

收录刊物：Scopus、SCIE

卷号：8

期号：3

页面范围：484-495

ISSN号：1705-5105

关键字：Double parallel feedforward neural network; gradient method; monotonicity; convergence

摘要：The deterministic convergence for a Double Parallel Feedforward Neural Network (DPFNN) is studied. DPFNN is a parallel connection of a multi-layer feedforward neural network and a single layer feedforward neural network. Gradient method is used for training DPFNN with finite training sample set. The monotonicity of the error function in the training iteration is proved. Then, some weak and strong convergence results are obtained, indicating that the gradient of the error function tends to zero and the weight sequence goes to a fixed point, respectively. Numerical examples are provided, which support our theoretical findings and demonstrate that DPFNN has faster convergence speed and better generalization capability than the common feedforward neural network.