公开(公告)号：US11537837B2

公开(公告)日：2022-12-27

申请号：US15883154

申请日：2018-01-30

Applicant: KLA-TENCOR CORPORATION

Inventor： Yuerui Chen ,  Xin Li

IPC: G06N3/04 ,  G06F17/16 ,  G06N3/08 ,  H01L21/66 ,  G03F7/20 ,  G01N21/47 ,  G01N21/21 ,  G01N21/95 ,  G06N20/10

Abstract: Techniques and systems for critical dimension metrology are disclosed. Critical parameters can be constrained with at least one floating parameter and one or more weight coefficients. A neural network is trained to use a model that includes a Jacobian matrix. During training, at least one of the weight coefficients is adjusted, a regression is performed on reference spectra, and a root-mean-square error between the critical parameters and the reference spectra is determined. The training may be repeated until the root-mean-square error is less than a convergence threshold.