Cascading Neural Network Blocks of Transistor Level Transceiver Models

Yixuan Zhao, Hanzhi Ma, Andreas Cangellaris, Er Ping Li, José E. Schutt-Ainé

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

Abstract

This paper presents a feed-forward neural network (FNN) framework devised for cascade-able transceiver behavior modeling. Voltage waveforms after each cascading block are predicted by the proposed method and directly fed to the next block as input. Unlike conventional IBIS-AMI models, FNN models do not interact with any SPICE-like transient solver, and hence are not limited by slow convergence or convolution. Comparison of accuracy and time efficiency are drawn and compared with a commercial simulation to demonstrate the effectiveness of employing FNN in transceiver macromodeling.

Original languageEnglish (US)
Title of host publication2022 Asia-Pacific International Symposium on Electromagnetic Compatibility, APEMC 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages7-9
Number of pages3
ISBN (Electronic)9781665416719
DOIs
StatePublished - 2022
Externally publishedYes
Event13th Asia-Pacific International Symposium on Electromagnetic Compatibility and Technical Exhibition, APEMC 2022 - Beijing, China
Duration: Sep 1 2022Sep 4 2022

Publication series

Name2022 Asia-Pacific International Symposium on Electromagnetic Compatibility, APEMC 2022

Conference

Conference13th Asia-Pacific International Symposium on Electromagnetic Compatibility and Technical Exhibition, APEMC 2022
Country/TerritoryChina
CityBeijing
Period9/1/229/4/22

Keywords

  • Transceiver modeling
  • channel simulation
  • feed-forward neural net-work
  • signal integrity

ASJC Scopus subject areas

  • Hardware and Architecture
  • Electrical and Electronic Engineering
  • Safety, Risk, Reliability and Quality
  • Radiation

Fingerprint

Dive into the research topics of 'Cascading Neural Network Blocks of Transistor Level Transceiver Models'. Together they form a unique fingerprint.

Cite this