An effective system for parameter optimization in photolithography process of a LGP stamper

Machine learning in electron beam lithography to boost photoresist formulation design for high-resolution patterning

“…[16][17][18][19][20][21][22][23][24][25][26] Photoresists usually contain a variety of components such as a photoacid generator (PAG), quencher as well as solvent, and their composition directly determines the imaging resolution of lithography. 27,28 Currently, in EBL experiments, the smaller critical dimensions (CDs) are mainly achieved by optimizing process conditions using trial and error, 29,30 and little attention has been paid to the photoresist formulation optimization. Screening suitable photoresist formulations remains a significant challenge due to the considerable time and high cost (Fig.…”

Critical dimension prediction of metal oxide nanoparticle photoresists for electron beam lithography using a recurrent neural network

“…21 Nevertheless, these methods will take a lot of time, especially for newly developed photoresists. To solve this problem, researchers have proposed process optimization methods based on a regression model, 22 a ternary gradient combination, 23 the Taguchi method, 24 a genetic algorithm, 21 and a particle swarm algorithm, 5 and have investigated the influence of process conditions on lithographic imaging. [13][14][15][16][25][26][27][28] However, these optimization methods still need a large number of experiments, and the corresponding relationship between process conditions and lithographic imaging performance cannot be determined.…”

“…Nowadays, machine learning methods are gradually being applied to the field of lithography, in which the most widely used is the multilayer feed-forward neural network (MFNN). At present, researchers have proposed process optimization approaches 5,21,[29][30][31][32][33] based on MFNN to obtain matching process conditions. Nevertheless, the MFNN model requires a large number of data sets to achieve high-precision predictive performance.…”

“…To improve the imaging quality of lithography, the most commonly used methods at present rely mainly on the experience of engineers and the trial and error method to determine the appropriate process conditions. 21 Nevertheless, these methods will take a lot of time, especially for newly developed photoresists. To solve this problem, researchers have proposed process optimization methods based on a regression model, 22 a ternary gradient combination, 23 the Taguchi method, 24 a genetic algorithm, 21 and a particle swarm algorithm, 5 and have investigated the influence of process conditions on lithographic imaging.…”

A survey on multi-objective hyperparameter optimization algorithms for Machine Learning

“…Finally, section 5 summarizes the findings, highlighting open challenges and potential solutions. focus on optimization of industrial processes (Chen, Jiang, Chang, & Chen, 2014), meta-learning (Vanschoren, 2019), optimization of internal parameters (Wawrzyński, 2017), and papers related to AutoML systems that are not focused on hyperparameter optimization (such as model selection algorithms (Silva et al, 2016;van Rijn, Abdulrahman, Brazdil, & Vanschoren, 2015) or pure feature selection methods (Hegde & Mundada, 2020)). Neural Architecture Search (NAS) is usually considered as a distinct category with its own methods and techniques for optimizing the structure of a neural network; hence, articles on NAS were only considered when the problem was addressed as an HPO problem.…”