RX equalization for a high-speed channel based on bayesian active learning using dropout

Xianbo Yang, Junyan Tang, Hakki M. Torun, Wiren D. Becker, Jose A. Hejase, Madhavan Swaminathan

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

5 Scopus citations

Abstract

Determining optimal equalization settings in highspeed bus design simulations is becoming more important due to increased complexity and data rates of current server systems, but it is also time and resource consuming. In this paper, a probabilistic machine learning technique, Bayesian Active Learning using Dropout (BAL-DO), is utilized to perform RX equalization and optimization to address this issue. Largest HEYE opening and corresponding equalization settings are obtained with high prediction accuracy without performing extensive time-domain analysis, thereby significantly reducing the cost of engineering time and computational resources.

Original languageEnglish (US)
Title of host publicationEPEPS 2020 - IEEE 29th Conference on Electrical Performance of Electronic Packaging and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728161617
DOIs
StatePublished - Oct 2020
Event29th IEEE Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2020 - San Jose, United States
Duration: Oct 5 2020Oct 7 2020

Publication series

NameEPEPS 2020 - IEEE 29th Conference on Electrical Performance of Electronic Packaging and Systems

Conference

Conference29th IEEE Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2020
Country/TerritoryUnited States
CitySan Jose
Period10/5/2010/7/20

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Energy Engineering and Power Technology

Fingerprint

Dive into the research topics of 'RX equalization for a high-speed channel based on bayesian active learning using dropout'. Together they form a unique fingerprint.

Cite this