Developing the Keep-Important-Samples Scheme for Training the Advanced CNN-Based Automatic Virtual Metrology Models

Abstract

Virtual Metrology (VM) technology can convert offline sampling inspection into online and real-time total inspection. As the processes of high-tech industries (semiconductor or TFT-LCD) are getting more sophisticated, higher VM prediction accuracy is demanded. With regard to this requirement, the advanced Convolutional-Neural-Networks (CNN) based VM system (denoted as Advanced AVM<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CNN</sub>) was proposed and verified to significantly enhance the overall prediction accuracy. Nevertheless, two issues need to be addressed to enhance the accuracy of the Advanced AVM<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CNN</sub> System: 1) rare and imbalanced collected metrology values lead to poor prediction accuracy of the extreme values, and 2) the model can only be updated when sufficient metrology values are collected. To tackle these problems, the Keep-Important-Samples (KIS) Scheme for the Advanced AVM<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CNN</sub> System is proposed in this letter with consideration of data balance. The experiments reveal that the proposed KIS Scheme can effectively enhance the prediction performance of the Advanced AVM<sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CNN</sub> System on the extreme values.