| 基于带偏差递归神经网络蛋白质关联图的预测 |
| |
| 引用本文： | 刘桂霞,于哲舟,周春光. 基于带偏差递归神经网络蛋白质关联图的预测[J]. 吉林大学学报(理学版), 2008, 46(2): 265-270 |
| |
| 作者姓名： | 刘桂霞 于哲舟 周春光 |
| |
| 作者单位： | 吉林大学 计算机科学与技术学院, 长春 130012 |
| |
| 基金项目： | 国家自然科学基金 , 国家自然科学基金 |
| |
| 摘 要： | 针对BP神经网络在学习速度方面的不足, 在Jordan和Elman网络结构的基础上, 提出一种带偏差单元的递归网络模型, 根据BP算法推导出该网络模型的权系数调整规则, 并应用该网络模型进行了蛋白质关联图预测的仿真分析. 结果表明, 该网络模型的收敛速度比一般BP网络有很大提高, 具有一定的实用性.
|
| 关 键 词： | 蛋白质关联图预测 人工神经网络 带偏差递归神经网络 疏水性 二级结构 |
| 文章编号： | 1671-5489(2008)02-0265-06 |
| 收稿时间： | 2007-05-04 |
| 修稿时间： | 2007-05-04 |
Prediction of Protein Contact Map Based onDeviation Units Recurrence Neural Network |
| |
| LIU Gui-xia,YU Zhe-zhou,ZHOU Chun-guang. Prediction of Protein Contact Map Based onDeviation Units Recurrence Neural Network[J]. Journal of Jilin University: Sci Ed, 2008, 46(2): 265-270 |
| |
| Authors: | LIU Gui-xia YU Zhe-zhou ZHOU Chun-guang |
| |
| Affiliation: | College of Computer Science and Technology, Jilin University, Changchun 130012, China |
| |
| Abstract: | To deal with the weakness of the BP neural network in learning speed, an Deviation Units Recurrence Neural Network model is presented based on the Jordan and Elman neural network. The weight regulatingmethod is developed based on BP algorithm. Simulations on fault diagnosis were performed with this neural network model. Experimental results show that the converging speed of this network model is faster than that of the traditional BP network and this model has a good practicability. |
| |
| Keywords: | prediction of protein contact maps artificial neural network deviation units recurrence neural network hydrophobicity secondary structure |
| 本文献已被 维普 万方数据 等数据库收录！ |
| 点击此处可从《吉林大学学报(理学版)》浏览原始摘要信息 |
|
点击此处可从《吉林大学学报(理学版)》下载全文 |
