高等学校化学学报 ›› 1998, Vol. 19 ›› Issue (6): 871.

• 论文 • 上一篇    下一篇

基于遗传算法的神经网络为苯乙酰胺类农药构效关系建模的研究

孙卫国, 陈德钊, 陈亚秋, 胡上序   

  1. 浙江大学化工系, 杭州, 310027
  • 收稿日期:1997-06-18 出版日期:1998-06-24 发布日期:1998-06-24
  • 通讯作者: 陈德钊
  • 作者简介:孙卫国,男,26岁,博±研究生.
  • 基金资助:

    浙江省自然科学基金

Model Building with Neural Networks Based on Genetic Algorithms for Structure-activity Relationships of Pesticide

SUN Wei-Guo, CHEN De-Zhao, CHEN Ya-Qiu, HU Shang-Xu   

  1. Department of Chemistry Engineering of Zhejiang University, Hangzhou, 310027
  • Received:1997-06-18 Online:1998-06-24 Published:1998-06-24

摘要: 探讨用遗传算法训练神经网络,为苯乙酰胺类化合物的QSAR建模,效果良好,神经网络可以反映复杂的构效关系,而引入遗传算法又有助于多层前传网在训练过程中跳出局部最小点,使收敛速度大大提高,并在预报精度上有显著改善.

关键词: 遗传算法, 神经网络, 农药, 构效关系, 建模

Abstract: In this paper, a neural network based on genetic algorithms was proposed for a QSAR model building of herbicidal N-(1-methyl-1-phenylethyl)phenylacetamides. Since neural networks can express complicated structure-activity relationships, and the combination of Genetic Algorithms can help the networks to jump out of the local optimal points, thus, it's peeds up the covergence of the training. At the same time, it's prediction precision has been notably raised.

Key words: Genetic algorithms, Neural networks, Herbicide, QSAR, Model building

中图分类号: 

TrendMD: