东华大学学报（英文版）2001，Vol.18Issue(1)：81-84,4.
Improving Adaptive Learning Rate of BP Neural Network for the Modelling of 3D Woven Composites Using the Golden Section Law
Improving Adaptive Learning Rate of BP Neural Network for the Modelling of 3D Woven Composites Using the Golden Section Law
易洪雷 1丁辛1
作者信息
- 1. College of Textiles, Dong Hua University, Shanghai, 200051
- 折叠
摘要
Abstract
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 train 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.关键词
BP algorithm/adaptive adjustment/network training parameter/learning strategy/network performance evaluationKey words
BP algorithm/adaptive adjustment/network training parameter/learning strategy/network performance evaluation分类
信息技术与安全科学引用本文复制引用
易洪雷,丁辛..Improving Adaptive Learning Rate of BP Neural Network for the Modelling of 3D Woven Composites Using the Golden Section Law[J].东华大学学报（英文版）,2001,18(1):81-84,4.
