2026-09-18T23:16:57Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/129156 2025-10-20 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms The student, Weiman Yan, accepted the attached license on 2025-03-28 at 15:23. The student, Weiman Yan, submitted this Thesis for approval on 2025-03-28 at 15:51. This Thesis was approved for publication on 2025-03-31 at 11:45. DSpace SAF Submission Ingestion Package generated from Vireo submission #21524 on 2025-10-19 at 18:08:34 Semantic autoencoder for modeling dielectric lifetime distributions Yan, Weiman 2025-03-31 Rosenbaum, Elyse Machine Learning Dielectric breakdown BEOL MOL TDDB Reliability eng This thesis presents a physics-based machine learning framework for modeling a dielectric lifetime distribution in the presence of manufacturing process variations. It uses a Semantic Autoencoder that provides insight into the dielectric thickness distribution and parameters of the underlying percolation model. Experiments show that the model is applicable to various types of dielectric films. The autoencoder may be configured to model intrinsic breakdown or to model breakdown resulting from competing failure mechanisms, e.g. intrinsic and extrinsic. 2025-05 Thesis https://hdl.handle.net/2142/129156 Copyright 2025 Weiman Yan Electrical & Computer Eng Electrical & Computer Engr University of Illinois Urbana-Champaign M.S. Thesis