| A Hybrid Learning Method for Multilayer Perceptrons |
| |
| 引用本文： | Zhao Meide Huang. A Hybrid Learning Method for Multilayer Perceptrons[J]. 哈尔滨工业大学学报, 1990, 0(3): 52-61 |
| |
| 作者姓名： | Zhao Meide Huang |
| |
| 摘 要： | A Newton learning method for a neural network of multilayer perceptrons is proposed in this paper. Furthermore, a hybrid learning method id legitimately developed in combination of the backpropagation method proposed by Rumelhart et al with the Newton learning method. Finally, the hybrid learning algorithm is compared with the backpropagation algorithm by some illustrations, and the results show that this hybrid leaming algorithm bas the characteristics of rapid convergence.
|
| 关 键 词： | 计算机 多层感知机 牛顿线性方法 神经网络 增殖算法 |
A Hybrid Learning Method for Multilayer Perceptrons |
| |
| Zhon Meide Huang Wenhu Hong Jiarong. A Hybrid Learning Method for Multilayer Perceptrons[J]. Journal of Harbin Institute of Technology, 1990, 0(3): 52-61 |
| |
| Authors: | Zhon Meide Huang Wenhu Hong Jiarong |
| |
| Affiliation: | School of Astronautics |
| |
| Abstract: | A Newton learning method for a neural network of multilayer perceptrons is proposed in this paper. Furthermore, a hybrid learning method id legitimately developed in combination of the backpropagation method proposed by Rumelhart et al with the Newton learning method. Finally, the hybrid learning algorithm is compared with the backpropagation algorithm by some illustrations, and the results show that this hybrid leaming algorithm bas the characteristics of rapid convergence. |
| |
| Keywords: | Computer Newton learning method neural network multilayer perceptron |
| 本文献已被 CNKI 维普 等数据库收录！ |
