公开(公告)号：WO2023001463A1

公开(公告)日：2023-01-26

申请号：PCT/EP2022/066798

申请日：2022-06-21

Applicant: ASML NETHERLANDS B.V.

Inventor： ADAL, Kedir, Mohammed ,  SAHRAEIAN, Reza ,  VAN DIJK, Leon, Paul ,  VAN HAREN, Richard, Johannes, Franciscus ,  HAQUE, Abu, Niyam, Md, Mushfiqul

IPC: G03F7/20 ,  G06N3/00

Abstract: Methods, systems, and apparatus for mapping high dimensional data related to a lithographic apparatus, etch tool, metrology tool or inspection tool to a lower dimensional representation of the data. High dimensional data is obtained related to the apparatus. The high dimensional data has first dimensions N greater than two. A nonlinear parametric model is obtained, which has been trained to map a training set of high dimensional data onto a lower dimensional representation. The lower dimensional representation has second dimensions M, wherein M is less than N. The model has been trained using a cost function configured to make the mapping preserve local similarities in the training set of high dimensional data. Using the model, the obtained high dimensional data is mapped to the corresponding lower dimensional representation.

公开(公告)号：EP4374226A1

公开(公告)日：2024-05-29

申请号：EP22738350.2

申请日：2022-06-21

Applicant: ASML Netherlands B.V.

Inventor： ADAL, Kedir, Mohammed ,  SAHRAEIAN, Reza ,  VAN DIJK, Leon, Paul ,  VAN HAREN, Richard, Johannes, Franciscus ,  HAQUE, Abu, Niyam, Md, Mushfiqul

IPC: G03F7/20 ,  G06N3/00

CPC classification number: G03F7/70508 ,  G03F7/705 ,  G03F7/70525

公开(公告)号：EP4130880A1

公开(公告)日：2023-02-08

申请号：EP21189299.7

申请日：2021-08-03

Applicant: ASML Netherlands B.V.

Inventor： ADAL, Kedir, Mohammed ,  SAHRAEIAN, Reza ,  VAN DIJK, Leon, Paul ,  VAN HAREN, Richard, Johannes, Franciscus ,  HAQUE, Abu, Niyam, Md, Mushfiqul

IPC: G03F7/20 ,  G06N3/00

Abstract: Methods, systems, and apparatus for mapping high dimensional data related to an apparatus to a lower dimensional representation of the data. High dimensional data is obtained related to the apparatus. The high dimensional data has first dimensions N greater than 2. A nonlinear parametric model is obtained, which has been trained to map a training set of high dimensional data onto a lower dimensional representation. The lower dimensional representation has second dimensions M, wherein M is less than N. The model has been trained using a cost function configured to make the mapping preserve local similarities in the training set of high dimensional data. Using the model, the obtained high dimensional data is mapped to the corresponding lower dimensional representation.