公开(公告)号：WO2020177973A1

公开(公告)日：2020-09-10

申请号：PCT/EP2020/052953

申请日：2020-02-06

Applicant: ASML NETHERLANDS B.V.

Inventor： LARRANAGA, Maialen ,  GKOROU, Dimitra ,  HASIBI, Faegheh ,  YPMA, Alexander

IPC: G03F7/20 ,  G06N3/04

Abstract: A method of extracting a feature from a data set includes iteratively extracting a feature (244) from a data set based on a visualization (238) of a residual pattern comprised within the data set, wherein the feature is distinct from a feature extracted in a previous iteration, and the visualization of the residual pattern uses the feature extracted in the previous iteration. Visualizing (234) the data set using the feature extracted in the previous iteration may comprise showing residual patterns of attribute data that are relevant to target data. Visualizing (234) the data set using the feature extracted in the previous iteration may involve adding cluster constraints to the data set, based on the feature extracted in the previous iteration. Additionally or alternatively, visualizing (234) the data set using the feature extracted in the previous iteration may involve defining conditional probabilities conditioned on the feature extracted in the previous iteration.

公开(公告)号：WO2020156724A1

公开(公告)日：2020-08-06

申请号：PCT/EP2019/084923

申请日：2019-12-12

Applicant: ASML NETHERLANDS B.V.

Inventor： HASIBI, Faegheh ,  VAN DIJK, Leon, Paul ,  LARRANAGA, Maialen ,  YPMA, Alexander ,  VAN HAREN, Richard, Johannes, Franciscus

IPC: G06N3/04 ,  G06N3/08

Abstract: According to an aspect of the disclosure there is provided a method for predicting a property associated with a product unit. The method may comprise obtaining a plurality of data sets, wherein each of the plurality of data sets comprises data associated with a spatial distribution of a parameter across the product unit, representing each of the plurality of data sets as a multidimensional object, obtaining a convolutional neural network model trained with previously obtained multidimensional objects and properties of previous product units, and applying the convolutional neural network model to the plurality of multidimensional objects representing the plurality of data sets, to predict the property associated with the product unit.

公开(公告)号：EP3935448A1

公开(公告)日：2022-01-12

申请号：EP20703998.3

申请日：2020-02-06

Applicant: ASML Netherlands B.V.

Inventor： LARRANAGA, Maialen ,  GKOROU, Dimitra ,  HASIBI, Faegheh ,  YPMA, Alexander

IPC: G03F7/20 ,  G06N3/04

公开(公告)号：EP3705944A1

公开(公告)日：2020-09-09

申请号：EP19160933.8

申请日：2019-03-06

Applicant: ASML Netherlands B.V.

Inventor： LARRANAGA, Maialen ,  GKOROU, Dimitra ,  HASIBI, Faegheh ,  YPMA, Alexander

IPC: G03F7/20 ,  G06N3/04

Abstract: A method of extracting a feature from a data set includes iteratively extracting a feature 244 from a data set based on a visualization 238 of a residual pattern comprised within the data set, wherein the feature is distinct from a feature extracted in a previous iteration, and the visualization of the residual pattern uses the feature extracted in the previous iteration. Visualizing 234 the data set using the feature extracted in the previous iteration may comprise showing residual patterns of attribute data that are relevant to target data. Visualizing 234 the data set using the feature extracted in the previous iteration may involve adding cluster constraints to the data set, based on the feature extracted in the previous iteration. Additionally or alternatively, visualizing 234 the data set using the feature extracted in the previous iteration may involve defining conditional probabilities conditioned on the feature extracted in the previous iteration.

公开(公告)号：EP3712817A1

公开(公告)日：2020-09-23

申请号：EP19164072.1

申请日：2019-03-20

Applicant: ASML Netherlands B.V.

Inventor： HASIBI, Faegheh ,  VAN DIJK, Leon, Paul ,  LARRANAGA, Maialen ,  YPMA, Alexander ,  VAN HAREN, Richard Johannes Franciscus

IPC: G06N3/04 ,  G06N3/08

Abstract: According to an aspect of the disclosure there is provided a method for predicting a property associated with a product unit. The method may comprise obtaining a plurality of data sets, wherein each of the plurality of data sets comprises data associated with a spatial distribution of a parameter across the product unit, representing each of the plurality of data sets as a multidimensional object, obtaining a convolutional neural network model trained with previously obtained multidimensional objects and properties of previous product units, and applying the convolutional neural network model to the plurality of multidimensional objects representing the plurality of data sets, to predict the property associated with the product unit.