Uncertainty Quantification with Invertible Neural Networks for Signal Integrity Applications

被引：0

作者：

Bhatti, Osama Waqar ^{[1
]}

Akinwande, Oluwaseyi ^{[1
]}

Swaminathan, Madhavan ^{[1
]}

机构：

[1] Georgia Inst Technol, Sch Elect & Comp Engn, Sch Mat Sci & Engn, 3D Syst Packaging Res Ctr PRC, Atlanta, GA 30332 USA

来源：

2022 IEEE MTT-S INTERNATIONAL CONFERENCE ON NUMERICAL ELECTROMAGNETIC AND MULTIPHYSICS MODELING AND OPTIMIZATION, NEMO | 2022年

基金：

美国国家科学基金会;

关键词：

Invertible neural networks; jacobian; uncertainty quantification; differential via-pair; signal integrity;

D O I：

10.1109/NEMO51452.2022.10038959

中图分类号：

C93 [管理学]; O22 [运筹学];

学科分类号：

070105 ; 12 ; 1201 ; 1202 ; 120202 ;

摘要：

We present a machine learning based tool to quantify uncertainty for prediction problems regarding signal integrity. Harnessing invertible neural networks, we convert the inverse posterior distribution given by the network to address uncertainty in frequency responses as a function of design space parameters. As an example, we consider a differential plated-through-hole via in package core and predict S-parameters from its geometrical properties. Results show 3.3% normalized mean squared error when compared with responses from a fullwave EM simulator.

引用

页数：4

共 50 条

[1] Conservative Gaussian Process Models for Uncertainty Quantification and Bayesian Optimization in Signal Integrity Applications
Manfredi, Paolo
IEEE TRANSACTIONS ON COMPONENTS PACKAGING AND MANUFACTURING TECHNOLOGY, 2024, 14 (07): : 1261 - 1272
[2] Photoacoustic Quantification of Tissue Oxygenation Using Conditional Invertible Neural Networks
Noelke, Jan-Hinrich
Adler, Tim J.
Schellenberg, Melanie
Dreher, Kris K.
Holzwarth, Niklas
Bender, Christoph J.
Tizabi, Minu D.
Seitel, Alexander
Maier-Hein, Lena
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2024, 43 (09) : 3366 - 3376
[3] Multiport VNA Measurement Uncertainty - Signal Integrity Applications
Grossman, Brett
Peterson, Michael
Torres, Jose
2011 IEEE INTERNATIONAL SYMPOSIUM ON ELECTROMAGNETIC COMPATIBILITY (EMC), 2011, : 619 - 623
[4] Uncertainty quantification for predictions of atomistic neural networks
Vazquez-Salazar, Luis Itza
Boittier, Eric D.
Meuwly, Markus
CHEMICAL SCIENCE, 2022, 13 (44) : 13068 - 13084
[5] A method for inferring signal strength modifiers by conditional invertible neural networks
Farkas, Mate Zoltan
Diekmann, Svenja
Eich, Niclas
Erdmann, Martin
26TH INTERNATIONAL CONFERENCE ON COMPUTING IN HIGH ENERGY AND NUCLEAR PHYSICS, CHEP 2023, 2024, 295
[6] Surrogate approach to uncertainty quantification of neural networks for regression
Kang, Myeonginn
Kang, Seokho
APPLIED SOFT COMPUTING, 2023, 139
[7] An Enhanced Particle Filter for Uncertainty Quantification in Neural Networks
Carannante, Giuseppina
Bouaynaya, Nidhal C.
Mihaylova, Lyudmila
2021 IEEE 24TH INTERNATIONAL CONFERENCE ON INFORMATION FUSION (FUSION), 2021, : 122 - 128
[8] Bayesian Neural Networks Uncertainty Quantification with Cubature Rules
Wang, Peng
He, Renke
Zhang, Qibin
Wang, Jikai
Mihaylova, Lyudmila
Bouaynaya, Nidhal C.
2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
[9] Uncertainty Quantification Methods for Neural Networks Pattern Recognition
Tolo, Silvia
Santhosh, T. V.
Vinod, Gopika
Oparaji, Uchenna
Patelli, Edoardo
2017 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI), 2017,
[10] Autoencoder-extended Conditional Invertible Neural Networks for Unfolding Signal Traces
Erdmann, M.
Hafner, K.
Schulte, J.
Straub, M.
20TH INTERNATIONAL WORKSHOP ON ADVANCED COMPUTING AND ANALYSIS TECHNIQUES IN PHYSICS RESEARCH, 2023, 2438

← 1 2 3 4 5 →