Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020109074 - METHOD FOR DECREASING UNCERTAINTY IN MACHINE LEARNING MODEL PREDICTIONS

Publication Number WO/2020/109074
Publication Date 04.06.2020
International Application No. PCT/EP2019/081774
International Filing Date 19.11.2019
IPC
G06N 3/04 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architecture, e.g. interconnection topology
G06N 3/08 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
G03F 1/36 2012.01
GPHYSICS
03PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
FPHOTOMECHANICAL PRODUCTION OF TEXTURED OR PATTERNED SURFACES, e.g. FOR PRINTING, FOR PROCESSING OF SEMICONDUCTOR DEVICES; MATERIALS THEREFOR; ORIGINALS THEREFOR; APPARATUS SPECIALLY ADAPTED THEREFOR
1Originals for photomechanical production of textured or patterned surfaces, e.g. masks, photo-masks or reticles; Mask blanks or pellicles therefor; Containers specially adapted therefor; Preparation thereof
36Masks having proximity correction features; Preparation thereof, e.g. optical proximity correction design processes
G03F 7/20 2006.01
GPHYSICS
03PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
FPHOTOMECHANICAL PRODUCTION OF TEXTURED OR PATTERNED SURFACES, e.g. FOR PRINTING, FOR PROCESSING OF SEMICONDUCTOR DEVICES; MATERIALS THEREFOR; ORIGINALS THEREFOR; APPARATUS SPECIALLY ADAPTED THEREFOR
7Photomechanical, e.g. photolithographic, production of textured or patterned surfaces, e.g. printed surfaces; Materials therefor, e.g. comprising photoresists; Apparatus specially adapted therefor
20Exposure; Apparatus therefor
CPC
G03F 1/36
GPHYSICS
03PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
FPHOTOMECHANICAL PRODUCTION OF TEXTURED OR PATTERNED SURFACES, e.g. FOR PRINTING, FOR PROCESSING OF SEMICONDUCTOR DEVICES; MATERIALS THEREFOR; ORIGINALS THEREFOR; APPARATUS SPECIALLY ADAPTED THEREFOR;
1Originals for photomechanical production of textured or patterned surfaces, e.g., masks, photo-masks, reticles; Mask blanks or pellicles therefor; Containers specially adapted therefor; Preparation thereof
36Masks having proximity correction features; Preparation thereof, e.g. optical proximity correction [OPC] design processes
G03F 7/70441
GPHYSICS
03PHOTOGRAPHY; CINEMATOGRAPHY; ANALOGOUS TECHNIQUES USING WAVES OTHER THAN OPTICAL WAVES; ELECTROGRAPHY; HOLOGRAPHY
FPHOTOMECHANICAL PRODUCTION OF TEXTURED OR PATTERNED SURFACES, e.g. FOR PRINTING, FOR PROCESSING OF SEMICONDUCTOR DEVICES; MATERIALS THEREFOR; ORIGINALS THEREFOR; APPARATUS SPECIALLY ADAPTED THEREFOR;
7Photomechanical, e.g. photolithographic, production of textured or patterned surfaces, e.g. printing surfaces; Materials therefor, e.g. comprising photoresists; Apparatus specially adapted therefor
70Exposure apparatus for microlithography
70425Imaging strategies, e.g. for increasing throughput, printing product fields larger than the image field, compensating lithography- or non-lithography errors, e.g. proximity correction, mix-and-match, stitching, double patterning
70433Layout for increasing efficiency, for compensating imaging errors, e.g. layout of exposure fields,; Use of mask features for increasing efficiency, for compensating imaging errors
70441Optical proximity correction
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 3/0472
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0472using probabilistic elements, e.g. p-rams, stochastic processors
G06N 3/082
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
082modifying the architecture, e.g. adding or deleting nodes or connections, pruning
G06N 3/084
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
084Back-propagation
Applicants
  • ASML NETHERLANDS B.V. [NL]/[NL]
Inventors
  • MIDDLEBROOKS, Scott, Anderson
  • VAN KRAAIJ, Markus, Gerardus, Martinus, Maria
  • PISARENCO, Maxim
Agents
  • PETERS, John Antoine
Priority Data
18209496.130.11.2018EP
19182658.526.06.2019EP
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) METHOD FOR DECREASING UNCERTAINTY IN MACHINE LEARNING MODEL PREDICTIONS
(FR) PROCÉDÉ DE RÉDUCTION D'INCERTITUDE DANS DES PRÉDICTIONS DE MODÈLE D'APPRENTISSAGE MACHINE
Abstract
(EN)
Described herein is a method for quantifying uncertainty in parameterized (e.g., machine learning) model predictions. The method comprises causing a parameterized model to predict multiple posterior distributions from the parameterized model for a given input. The multiple posterior distributions comprise a distribution of distributions. The method comprises determining a variability of the predicted multiple posterior distributions for the given input by sampling from the distribution of distributions; and using the determined variability in the predicted multiple posterior distributions to quantify uncertainty in the parameterized model predictions. The parameterized model comprises encoder-decoder architecture. The method comprises using the determined variability in the predicted multiple posterior distributions to adjust the parameterized model to decrease the uncertainty of the parameterized model for predicting wafer geometry, overlay, and/or other information as part of a semiconductor manufacturing process.
(FR)
L'invention concerne un procédé de quantification d'incertitude dans des prédictions de modèle paramétrées (par exemple, apprentissage machine). Le procédé consiste à amener un modèle paramétré à prédire de multiples distributions postérieures à partir du modèle paramétré pour une entrée donnée. Les multiples distributions postérieures comprennent une distribution de distributions. Le procédé comprend la détermination d'une variabilité des distributions postérieures multiples prédites pour l'entrée donnée par échantillonnage à partir de la distribution de distributions ; et l'utilisation de la variabilité déterminée dans les multiples distributions postérieures prédites pour quantifier l'incertitude dans les prédictions de modèle paramétrées. Le modèle paramétré comprend une architecture de codeur-décodeur. Le procédé comprend l'utilisation de la variabilité déterminée dans les multiples distributions postérieures prédites pour ajuster le modèle paramétré de façon à diminuer l'incertitude du modèle paramétré pour prédire une géométrie de tranche, un recouvrement et/ou d'autres informations en tant que partie d'un processus de fabrication de semi-conducteur.
Also published as
Latest bibliographic data on file with the International Bureau