摘要:
Automated determination of a number of profiles for a training data set to be used in training a machine learning system for generating target function information from modeled profile parameters. In one embodiment, a first principal component analysis (PCA) is performed on a training data set, and a second PCA is performed on a combined data set which includes the training data set and a test data set. A test data set estimate is generated based on the first PCA transform and the second PCA matrix. The size of error between the test data set and the test data set estimate is used to determine whether a number of profiles associated with the training data set is sufficiently large for training a machine learning system to generate a library of spectral information.
摘要:
Automated determination of a number of profiles for a training data set to be used in training a machine learning system for generating target function information from modeled profile parameters. In one embodiment, a first principal component analysis (PCA) is performed on a training data set, and a second PCA is performed on a combined data set which includes the training data set and a test data set. A test data set estimate is generated based on the first PCA transform and the second PCA matrix. The size of error between the test data set and the test data set estimate is used to determine whether a number of profiles associated with the training data set is sufficiently large for training a machine learning system to generate a library of spectral information.
摘要:
Embodiments are generally directed to neural network training for library-based critical dimension metrology. An embodiment of a method includes optimizing a threshold for a principal component analysis of a spectrum data set to provide a principal component value, estimating a training target for one or more neural networks, training the one or more neural networks based both on the training target and on the principal component value provided from optimizing the threshold for the principal component analysis, and providing a spectral library based on the one or more trained neural networks.
摘要:
Approaches for accurate neural network training for library-based critical dimension (CD) metrology are described. Approaches for fast neural network training for library-based CD metrology are also described. In an example, a method includes optimizing a threshold for a principal component analysis (PCA) of a spectrum data set to provide a principal component (PC) value, estimating a training target for one or more neural networks, training the one or more neural networks based both on the training target and on the PC value provided from optimizing the threshold for the PCA, and providing a spectral library based on the one or more trained neural networks.
摘要:
Approaches for accurate neural network training for library-based critical dimension (CD) metrology are described. Approaches for fast neural network training for library-based CD metrology are also described.
摘要:
A profile parameter value is determined in integrated circuit metrology by: a) determining a diffraction signal difference based on a measured diffraction signal and a previously generated diffraction signal; b) determining a first profile parameter value based on the previously generated diffraction signal; c) determining a first profile parameter value change based on the diffraction signal difference; d) determining a second profile parameter value based on the first profile parameter value change; e) determining a second profile parameter value change between the first and second profile parameter values; f) determining if the second profile parameter value change meets one or more preset criteria; and g) when the second profile parameter value change fails to meet the one or more preset criteria, iterating c) to g) using as the diffraction signal difference in the iteration of step c), a diffraction signal difference determined based on the measured diffraction signal and a diffraction signal for the second profile parameter value previously determined in step d), and as the first profile parameter value in the iteration of step e), the second profile parameter value previously determined in step d).
摘要:
Approaches for accurate neural network training for library-based critical dimension (CD) metrology are described. Approaches for fast neural network training for library-based CD metrology are also described.
摘要:
Metrology data from a semiconductor treatment system is transformed using multivariate analysis. In particular, a set of metrology data measured or simulated for one or more substrates treated using the treatment system is obtained. One or more essential variables for the obtained set of metrology data is determined using multivariate analysis. A first metrology data measured or simulated for one or more substrates treated using the treatment system is obtained. The first obtained metrology data is not one of the metrology data in the set of metrology data earlier obtained. The first metrology data is transformed into a second metrology data using the one or more of the determined essential variables.
摘要:
To manage data flow in generating profile models for use in optical metrology, a project data object is created. A first profile model data object is created. The first profile model data object corresponds to a first profile model defined using profile parameters. A version number is associated with the first profile model data object. The first profile model data object is linked with the project data object. At least a second profile model data object is created. The second profile model data object corresponds to a second profile model defined using profile parameters. The first and second profile models are different. Another version number is associated with the second profile model data object. The second profile model data object is linked with the project data object. The project data object, the first profile model data object, and the second profile model data object are stored. The version numbers associated with the first profile model data object and the second profile model data object are stored. The link between the first profile model data object and the project data object is stored. The link between the second profile model data object and the project data object is stored.
摘要:
An optical metrology model for a structure to be formed on a wafer is developed by characterizing a top-view profile and a cross-sectional view profile of the structure using profile parameters. The profile parameters of the top-view profile and the cross-sectional view profile are integrated together into the optical metrology model. The profile parameters of the optical metrology model are saved.