More Information
Summary:Described herein is a method for adjusting a prediction model used for enhancing a lithography process. The method comprises providing (400) an initial prediction model (401) comprising a plurality of model parameters to one or more remote locations (404). The method comprises training (420) the initial prediction model with local data (406) at the one or more remote locations (404) such that at least one model parameter (W) is updated (450,454,454). The method comprises receiving (460) the at least one updated model parameter from each of the one or more remote locations where the initial prediction model was trained. The method comprises determining aggregated updated model parameters based on the at least one updated model parameter received from the one or more remote locations. The method comprises adjusting the initial prediction model based on the aggregated updated model parameters. The adjusted prediction model is operable to enhance the lithography process.
Bibliography:Application Number: EP20190175717