Volterra Kernel Extraction through Monomial Power Series Feed Forward Neural Network for Behavior Modeling of High Speed I/O Buffer

Xinying Wang, Thong Nguyen, Jose Schutt-Aine

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

Abstract

This work explores Volterra kernel extraction using feed forward neural network (FFN) with monomial power series (MPS) activation function for high speed I/O buffer behavioral modeling. The proposed method demonstrates a higher level of accuracy and flexible order truncation. The proposed method is validated using a computer simulated Weiner system with second order nonlinearity. A case study with a real high speed I/O buffer is also conducted and discussed.

Original languageEnglish (US)
Title of host publication2019 Joint International Symposium on Electromagnetic Compatibility, Sapporo and Asia-Pacific International Symposium on Electromagnetic Compatibility, EMC Sapporo/APEMC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages564-567
Number of pages4
ISBN (Electronic)9784885523229
DOIs
StatePublished - Jun 2019
Event2019 Joint International Symposium on Electromagnetic Compatibility, Sapporo and Asia-Pacific International Symposium on Electromagnetic Compatibility, EMC Sapporo/APEMC 2019 - Sapporo, Japan
Duration: Jun 3 2019Jun 7 2019

Publication series

Name2019 Joint International Symposium on Electromagnetic Compatibility, Sapporo and Asia-Pacific International Symposium on Electromagnetic Compatibility, EMC Sapporo/APEMC 2019

Conference

Conference2019 Joint International Symposium on Electromagnetic Compatibility, Sapporo and Asia-Pacific International Symposium on Electromagnetic Compatibility, EMC Sapporo/APEMC 2019
Country/TerritoryJapan
CitySapporo
Period6/3/196/7/19

Keywords

  • Behavior Modeling
  • Feed Forward Neural Network
  • Signal Integrity
  • Volterra Series

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Information Systems and Management

Fingerprint

Dive into the research topics of 'Volterra Kernel Extraction through Monomial Power Series Feed Forward Neural Network for Behavior Modeling of High Speed I/O Buffer'. Together they form a unique fingerprint.

Cite this