神经网络B－P学习算法及其在含F铋系高温超导体制备中的应用  

B-P LEARNING ALGORITHM OF NEURAL NETWORK AND ITS APPLICATION TO THE SYNTHESIS OF HIGH-T_c SUPERCONDUCTOR Bi-BASED DOPED F

作　　者：蔡煜东[1] 刘洪霖[1] 甘俊人 姚林声 陈念贻[1] 

机构地区：[1]中国科学院上海冶金研究所

出　　处：《应用科学学报》1994年第3期253-258,共6页Journal of Applied Sciences

摘　　要：叙述“反向传播”神经网络的结构、算法及其在含Ｆ铋系高温超导体制备中的应用．实验结果表明神经网络的判别正确率为１００％．因此，该方法可用于材料设计等高层次知识处理领域．Great attention is now being paid to neural network in pattern recognitionand other fields. The structure of neural network,the back propagation algorithmfor neural network and its application to the synthesis of high-T_c superconductorBi-based doped F are presented in this paper.The experimental results show thatthe performance of the neural network model is good,and therefore the modelmay be used in material design and other fields.

关 键 词：神经网络 学习算法 铋系 超导体 

分 类 号：TM26[一般工业技术—材料科学与工程]