APPLICATION OF NEURAL NETWORK AUTO ENCODERS OF UNET TYPE FOR INVERSE PHOTOLITOGRAPHY TASKS

Abstract

The paper discusses the issue of the applicability of neural networks to the problems of designing microelectronics. The integration of neural network modules into the elements of specialized EDA systems can significantly speed up the modeling processes at different stages of design. The application of a multilayer convolutional architecture of a neural network of the UNET type to the problem of direct and inverse computational photolithography is considered. Using this neural network approach, we were able to speed up the computation of a photo mask for a 90nm process technology by two orders of magnitude and achieve simulation accuracy that surpasses standard inverse photolithography (ILT) methods.