Semiconductor Manufacturing Yield Prediction System and Method based on Machine Learning

摘要

A machine learning based semiconductor manufacturing yield prediction system and method are provided. The result prediction method according to the embodiment of the present invention classifies different types of data according to types and inputs them to different neural network models to learn neural network models, To predict the resultant value. Thus, different neural network models can be applied according to the type of data, and accurate result values can be predicted by securing a neural network model having a structure suited to the characteristics of data.