Semantic autoencoder for modeling dielectric lifetime distributions

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.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Electrical & Computer Engr

Grantor

University of Illinois Urbana-Champaign

Year dc:date

2025

Author dc:creator

• Yan, Weiman

Contributors dc:contributor

• Rosenbaum, Elyse

• Machine Learning
• Dielectric breakdown
• BEOL
• MOL
• TDDB
• Reliability

Statement dc:rights

• Copyright 2025 Weiman Yan

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/129156

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F129156