A method for creating behavioral models of oscillators using augmented neural networks

Huan Yu, Madhavan Swaminathan, Chuanyi Ji, David White

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

8 Scopus citations

Abstract

This paper describes a novel technique to model the nonlinear time-domain behavior of oscillators using augmented neural networks. In the proposed method, a feed forward neural network with a periodic unit is used to capture the periodicity of the oscillatory output waveform. As opposed to the state space model, which is based on a system of differential equations, the output of the oscillator is generated explicitly using the neural network presented in this paper. The model is trained using the data obtained from the simulation of transistor-level circuit models. Examples applied to ring oscillators show the advantages using this method based on CPU time and accuracy. The proposed model is compatible with Verilog-A.

Original languageEnglish (US)
Title of host publication2017 IEEE 26th Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-3
Number of pages3
ISBN (Electronic)9781467364836
DOIs
StatePublished - Jul 2 2017
Event26th IEEE Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2017 - San Jose, United States
Duration: Oct 15 2017Oct 18 2017

Publication series

Name2017 IEEE 26th Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2017
Volume2018-January

Conference

Conference26th IEEE Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2017
Country/TerritoryUnited States
CitySan Jose
Period10/15/1710/18/17

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Computer Networks and Communications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'A method for creating behavioral models of oscillators using augmented neural networks'. Together they form a unique fingerprint.

Cite this