| 基于遗传算法的神经网络分类器 |
| |
| 引用本文： | 梁化楼,戴贵亮.基于遗传算法的神经网络分类器[J].核电子学与探测技术,1996,16(3):174-176,224. |
| |
| 作者姓名： | 梁化楼 戴贵亮 |
| |
| 作者单位： | 中国科学院高能物理研究所计算中心 |
| |
| 摘 要： | 本文基于遗传算法和级联相关算法的组合，提出了遗传辅助级联相关学习算法。该算法能够根据问题的需要自动设计网络结构，同时能有效地消除竞争协议问题。实验结果表明，与级联相关算法相比，它具有结构紧紧，泛化能力好等优点。
|
| 关 键 词： | 遗传算法 级联相关 神经网络 |
Neural Network Classmer Based on Genetic Algorithm |
| |
| Liang Hualou,Dai Guiliang.Neural Network Classmer Based on Genetic Algorithm[J].Nuclear Electronics & Detection Technology,1996,16(3):174-176,224. |
| |
| Authors: | Liang Hualou Dai Guiliang |
| |
| Abstract: | Based on genetic technique and cascade correlation algorithm,a new constructive algorithm for connectionistlearning,genetic aided cascade correlation algorithm,is proposed It can automatically grow the architecture ofne ural network to give a suitable n etwork size for a spoc ific problem and is free of the competing conventionsproblem. Experimental results show that the network obtained with our technique is of small size and has ex-cellent performance compared with the normal cascade correlation learning algorithm.( |
| |
| Keywords: | Geneticalgorithm Cascade correlation Neural network) |
| 本文献已被 CNKI 维普 等数据库收录！ |
