Semiconductor defect classification using hyperellipsoid clustering neural networks and model switching
Semiconductor defect classification using hyperellipsoid clustering neural networks and model switching
复制标题
使用超椭球聚类神经网络和模型切换进行半导体缺陷分类
DOI：
10.1109/ijcnn.1999.836231
复制
发表时间：
1999
期刊：
影响因子：
--
通讯作者：
Y. Kosugi
中科院分区：
文献类型：
--
作者：
K. Kameyama;Y. Kosugi
引入了一种使用神经网络分类器对半导体晶圆进行视觉检测的自动缺陷分类（ADC）系统。所提出的超椭球聚类网络（HCN）在隐藏层中采用径向基函数（RBF），并使用附加惩罚条件进行训练，以将不熟悉的输入识别为源自未知缺陷类别。此外，通过使用称为模型切换的动态模型改变方法，获得了能够进行有效分类的简化模型分类器。在实验中，确认了陌生输入识别的有效性，并且获得了足够高的分类率以用于半导体工厂。
An automatic defect classification (ADC) system for visual inspection of semiconductor wafers, using a neural network classifier is introduced The proposed hyperellipsoid clustering network (HCN) employing a radial basis function (RBF) in the hidden layer is trained with additional penalty conditions for recognizing unfamiliar inputs as originating from an unknown defect class. Also, by using a dynamic model alteration method called model switching, a reduced-model classifier which enables an efficient classification is obtained In the experiments, the effectiveness of the unfamiliar input recognition was confirmed, and a classification rate sufficiently high for use in the semiconductor fab was obtained.