Dynamic control of machine learning based measurement recipe optimization

Abstract

Methods and systems for training and implementing metrology recipes while dynamically controlling the convergence trajectories of multiple performance objectives are described herein. Performance metrics are employed to regularize the optimization process employed during measurement model training, model-based regression, or both. Weighting values associated with each of the performance objectives in the loss function of the model optimization are dynamically controlled during model training. In this manner, convergence of each performance objective and the tradeoff between multiple performance objectives of the loss function is controlled to arrive at a trained measurement model in a stable, balanced manner. A trained measurement model is employed to estimate values of parameters of interest based on measurements of structures having unknown values of one or more parameters of interest. In another aspect, weighting values associated with each of the performance objectives in a model-based regression on a measurement model are dynamically controlled.