摘要
分别讨论了最小二乘法和神经网络法用于电子光学透镜逆设计的情况,并比较了各自优缺点。可以看到在较好的选取学习样本情况下,神经网络技术在电子透镜的逆设计中有着明显的优越性。
The application of damped least square method and the artificial neural network to inverse designing the electronic lens and their merits and defects are discussed in this paper.In the condition of selecting the learning samples properly,the artificial neural network has the obvious advantage in the inverse designing the electronic lens.It is an effective method of solving the inverse designing problem in the electronic optical system.
出处
《真空电子技术》
2000年第1期15-19,共5页
Vacuum Electronics
基金
国家教委留学回国人员科研启动基金
关键词
电子光学透镜
逆设计
神经网络
电子透镜
Inverse design of electron optical lens
Damped least squares method
artificial neural network
