论文部分内容阅读
Focused on various BP algorithms with variable learning rate based on network system error gradient, a modified learning strategy for training non-linear network models is developed with both the incremental and the decremental factors of network learning rate being adjusted adaptively and dynamically. The golden section law is put forward to build a relationship between the network training parameters, and a series of data from an existing model is used to tram and test the network parameters. By means of the evaluation of network performance in respect to convergent speed and predicting precision, the effectiveness of the proposed learning strategy can be illustrated.
Focused on various BP algorithms with variable learning rate based on network system error gradient, a modified learning strategy for training non-linear network models is developed with both the incremental and the decremental factors of network learning rate being adjusted adaptively and dynamically. The golden section law is put forward to build a relationship between the network training parameters, and a series of data from an existing model is used to tram and test the network parameters. By means of the evaluation of network performance in respect to convergent speed and predicting precision, the effectiveness of the proposed learning strategy can be illustrated.