| 计算机辅助材料设计的偏最小二乘法－人工神经网络研究 |
| |
| 引用本文： | 郭进,刘洪霖,黄铁生,陈念贻. 计算机辅助材料设计的偏最小二乘法－人工神经网络研究[J]. 计算机与应用化学, 1996, 0(4) |
| |
| 作者姓名： | 郭进 刘洪霖 黄铁生 陈念贻 |
| |
| 作者单位： | 中国科学院上海冶金研究所 |
| |
| 基金项目： | 国家自然科学基金,“863”资助 |
| |
| 摘 要： | 在噪声小的ＰＬＳ（偏最小二乘法）空间上，样本集的局部投影可被用作ＢＰＮ（反向传播网络）的输入元素以建立一种“平衡”的神经网络结构，这种结构在很大程度上克服了通常ＢＰＮ过拟合的缺点。在ＰＬＳ子空间优化区，利用非线性逆映照技术设计的基于期望目标值的样本可通过ＰＬＳ－ＰＮ方法预报和选取。本文还利用此方法设计了若干以初始容量为目标的Ｎｉ／ＭＨ电池阴极材料。
|
| 关 键 词： | 人工神经网络，偏最小二乘法，材料设计 |
APPLICATION OF PARTIAL LEAST SQUARE-ARTIFICIAL NEURAL NETWORK METHOD IN COMPUTER-AIDED MATERIALS DESIGN |
| |
| Guo Jin, Liu Honglin,Huang Tiesheng,Chen Nianyi. APPLICATION OF PARTIAL LEAST SQUARE-ARTIFICIAL NEURAL NETWORK METHOD IN COMPUTER-AIDED MATERIALS DESIGN[J]. Computers and Applied Chemistry, 1996, 0(4) |
| |
| Authors: | Guo Jin Liu Honglin Huang Tiesheng Chen Nianyi |
| |
| Abstract: | The partial projection of sample set with less noise in Partial Least Square(PLS) space is used as input elements of Back Propagation Network (BPN)to build a balance neural network structure which can overcome the shortcoming of overfitting in BPN in a great extent.In the optimal region of PLS sub-space,the samples,which are based on the predicted target values and designed by the non-linear inverse mapping technique,can be predicted and selected using PLS-BPN method, The PLS-BPN method is applied in design of the cathode material of the Ni/MH battery. |
| |
| Keywords: | Partial least square Artificial neural network Materials design |
| 本文献已被 CNKI 等数据库收录！ |
|
