Mentor: Dr. Jinchuan ShiManager: Dr. Phillip Atkins
Neural network solution for KLA AcuShape# chip architecture software
• Developed neural network to realize geometry critical dimension (CD) and spectra prediction/validation for Samsung V-NAND devices, substituting RCWA numerical method in the design loop.
• Designed bidirectional-training networks to accomplish software library generation with an 80% smaller training dataset and better linearity performance.
Investigate effective device degree-of-freedom (DOF) reduction via generative AI
• Built up a variational autoencoder-based model to effectively reconstruct and sample large DOF geometry critical dimensions (CD) of semiconductor devices into decreased DOF in compressed latent space.
• Perturbed compressed DOF CDs during high-quality spectra output regression optimization and decreased 70% of regression iterations/simulation resource usage.
Optical Engineer Intern
09/2017 - 05/2018
Xingyu Automotive Lighting Systems (Changzhou, China)
Skills:
C/C++
Ansys
Ze
Zemax
So
SolidWorks
Au
AutoCAD
EM
EM Simulation
Comsol
Ma
Matlab
High-pixel digital lighting unit design
• Applied 3D modeling and optical trace simulations to design high-pixel, independently adjustable LED light matrices.
• Developed customized lighting projection functions for driving assistance in BMW lighting system team.