Verilog-A compatible recurrent neural network model for transient circuit simulation

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

Abstract

This paper presents a method for data-driven behavioral modeling of electronic circuits using recurrent neural networks (RNNs). The RNN structure is adapted based on known characteristics of the system being modeled. The discrete-time RNN is transformed to a continuous-time model and then implemented in Verilog-A for compatibility with general-purpose circuit simulators.

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
Volume2018-January
ISBN (Electronic)9781467364836
DOIs
StatePublished - Apr 2 2018
Event26th IEEE Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2017 - San Jose, United States
Duration: Oct 15 2017Oct 18 2017

Other

Other26th IEEE Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2017
CountryUnited States
CitySan Jose
Period10/15/1710/18/17

Fingerprint

Computer hardware description languages
Recurrent neural networks
Circuit simulation
Networks (circuits)
Simulators

Keywords

  • Behavioral models
  • Circuit simulation
  • Recurrent neural network
  • Verilog-A

ASJC Scopus subject areas

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

Cite this

Chen, Z., Raginsky, M., & Rosenbaum, E. (2018). Verilog-A compatible recurrent neural network model for transient circuit simulation. In 2017 IEEE 26th Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2017 (Vol. 2018-January, pp. 1-3). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EPEPS.2017.8329743

Verilog-A compatible recurrent neural network model for transient circuit simulation. / Chen, Zaichen; Raginsky, Maxim; Rosenbaum, Elyse.

2017 IEEE 26th Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-3.

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

Chen, Z, Raginsky, M & Rosenbaum, E 2018, Verilog-A compatible recurrent neural network model for transient circuit simulation. in 2017 IEEE 26th Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2017. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 1-3, 26th IEEE Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2017, San Jose, United States, 10/15/17. https://doi.org/10.1109/EPEPS.2017.8329743
Chen Z, Raginsky M, Rosenbaum E. Verilog-A compatible recurrent neural network model for transient circuit simulation. In 2017 IEEE 26th Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2017. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-3 https://doi.org/10.1109/EPEPS.2017.8329743
Chen, Zaichen ; Raginsky, Maxim ; Rosenbaum, Elyse. / Verilog-A compatible recurrent neural network model for transient circuit simulation. 2017 IEEE 26th Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-3
@inproceedings{868a153709a348f4abf442c246a0151e,
title = "Verilog-A compatible recurrent neural network model for transient circuit simulation",
abstract = "This paper presents a method for data-driven behavioral modeling of electronic circuits using recurrent neural networks (RNNs). The RNN structure is adapted based on known characteristics of the system being modeled. The discrete-time RNN is transformed to a continuous-time model and then implemented in Verilog-A for compatibility with general-purpose circuit simulators.",
keywords = "Behavioral models, Circuit simulation, Recurrent neural network, Verilog-A",
author = "Zaichen Chen and Maxim Raginsky and Elyse Rosenbaum",
year = "2018",
month = "4",
day = "2",
doi = "10.1109/EPEPS.2017.8329743",
language = "English (US)",
volume = "2018-January",
pages = "1--3",
booktitle = "2017 IEEE 26th Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Verilog-A compatible recurrent neural network model for transient circuit simulation

AU - Chen, Zaichen

AU - Raginsky, Maxim

AU - Rosenbaum, Elyse

PY - 2018/4/2

Y1 - 2018/4/2

N2 - This paper presents a method for data-driven behavioral modeling of electronic circuits using recurrent neural networks (RNNs). The RNN structure is adapted based on known characteristics of the system being modeled. The discrete-time RNN is transformed to a continuous-time model and then implemented in Verilog-A for compatibility with general-purpose circuit simulators.

AB - This paper presents a method for data-driven behavioral modeling of electronic circuits using recurrent neural networks (RNNs). The RNN structure is adapted based on known characteristics of the system being modeled. The discrete-time RNN is transformed to a continuous-time model and then implemented in Verilog-A for compatibility with general-purpose circuit simulators.

KW - Behavioral models

KW - Circuit simulation

KW - Recurrent neural network

KW - Verilog-A

UR - http://www.scopus.com/inward/record.url?scp=85049745587&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049745587&partnerID=8YFLogxK

U2 - 10.1109/EPEPS.2017.8329743

DO - 10.1109/EPEPS.2017.8329743

M3 - Conference contribution

AN - SCOPUS:85049745587

VL - 2018-January

SP - 1

EP - 3

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

PB - Institute of Electrical and Electronics Engineers Inc.

ER -