A machine learning methodology for inferring network S-parameters in the presence of variability

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes the use of Variational Autoencoders, a generative modeling technique, for the problem of inferring S-parameters of linear multiport networks in the presence of manufacturing variability. The Variational Autoencoder learns the underlying data generation process and yields a generative network that can approximately mimic the probability distribution of the training data. The generated samples can be used for subsequent statistical simulations. A post-processing step, applying Vector Fitting to the predicted S-parameters, constrains the model to a finite-order rational function form and enforces appropriate physical constraints. The method is validated through its application to a coupled micro strip transmission line.

Original languageEnglish (US)
Title of host publication2018 IEEE 22nd Workshop on Signal and Power Integrity, SPI 2018 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-4
Number of pages4
ISBN (Electronic)9781538622995
DOIs
StatePublished - Jun 29 2018
Event22nd IEEE Workshop on Signal and Power Integrity, SPI 2018 - Brest, France
Duration: May 22 2018May 25 2018

Publication series

Name2018 IEEE 22nd Workshop on Signal and Power Integrity, SPI 2018 - Proceedings

Other

Other22nd IEEE Workshop on Signal and Power Integrity, SPI 2018
CountryFrance
CityBrest
Period5/22/185/25/18

Keywords

  • Bayes methods
  • Inference algorithms
  • Integrated circuit interconnections
  • Statistical analysis
  • Unsupervised learning

ASJC Scopus subject areas

  • Signal Processing
  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering
  • Safety, Risk, Reliability and Quality

Fingerprint Dive into the research topics of 'A machine learning methodology for inferring network S-parameters in the presence of variability'. Together they form a unique fingerprint.

  • Cite this

    Ma, X., Raginsky, M., & Cangellaris, A. C. (2018). A machine learning methodology for inferring network S-parameters in the presence of variability. In 2018 IEEE 22nd Workshop on Signal and Power Integrity, SPI 2018 - Proceedings (pp. 1-4). (2018 IEEE 22nd Workshop on Signal and Power Integrity, SPI 2018 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SaPIW.2018.8401643