Cascading Neural Network Blocks of Transistor Level Transceiver Models

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

doi:10.1109/APEMC53576.2022.9888478

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 proceeding › Conference 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 language	English (US)
Title of host publication	2022 Asia-Pacific International Symposium on Electromagnetic Compatibility, APEMC 2022
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	7-9
Number of pages	3
ISBN (Electronic)	9781665416719
DOIs	https://doi.org/10.1109/APEMC53576.2022.9888478
State	Published - 2022
Event	13th Asia-Pacific International Symposium on Electromagnetic Compatibility and Technical Exhibition, APEMC 2022 - Beijing, China Duration: Sep 1 2022 → Sep 4 2022

Publication series

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

Conference

Conference	13th Asia-Pacific International Symposium on Electromagnetic Compatibility and Technical Exhibition, APEMC 2022
Country/Territory	China
City	Beijing
Period	9/1/22 → 9/4/22

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

Online availability

10.1109/APEMC53576.2022.9888478

Library availability

Discover UIUC Full Text

Cite this

Zhao, Y., Ma, H., Cangellaris, A., Li, E. P., & Schutt-Ainé, J. E. (2022). Cascading Neural Network Blocks of Transistor Level Transceiver Models. In 2022 Asia-Pacific International Symposium on Electromagnetic Compatibility, APEMC 2022 (pp. 7-9). (2022 Asia-Pacific International Symposium on Electromagnetic Compatibility, APEMC 2022). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/APEMC53576.2022.9888478

Cascading Neural Network Blocks of Transistor Level Transceiver Models. / Zhao, Yixuan; Ma, Hanzhi; Cangellaris, Andreas et al.
2022 Asia-Pacific International Symposium on Electromagnetic Compatibility, APEMC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. p. 7-9 (2022 Asia-Pacific International Symposium on Electromagnetic Compatibility, APEMC 2022).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Zhao, Y, Ma, H, Cangellaris, A, Li, EP & Schutt-Ainé, JE 2022, Cascading Neural Network Blocks of Transistor Level Transceiver Models. in 2022 Asia-Pacific International Symposium on Electromagnetic Compatibility, APEMC 2022. 2022 Asia-Pacific International Symposium on Electromagnetic Compatibility, APEMC 2022, Institute of Electrical and Electronics Engineers Inc., pp. 7-9, 13th Asia-Pacific International Symposium on Electromagnetic Compatibility and Technical Exhibition, APEMC 2022, Beijing, China, 9/1/22. https://doi.org/10.1109/APEMC53576.2022.9888478

Zhao Y, Ma H, Cangellaris A, Li EP, Schutt-Ainé JE. Cascading Neural Network Blocks of Transistor Level Transceiver Models. In 2022 Asia-Pacific International Symposium on Electromagnetic Compatibility, APEMC 2022. Institute of Electrical and Electronics Engineers Inc. 2022. p. 7-9. (2022 Asia-Pacific International Symposium on Electromagnetic Compatibility, APEMC 2022). doi: 10.1109/APEMC53576.2022.9888478

Zhao, Yixuan ; Ma, Hanzhi ; Cangellaris, Andreas et al. / Cascading Neural Network Blocks of Transistor Level Transceiver Models. 2022 Asia-Pacific International Symposium on Electromagnetic Compatibility, APEMC 2022. Institute of Electrical and Electronics Engineers Inc., 2022. pp. 7-9 (2022 Asia-Pacific International Symposium on Electromagnetic Compatibility, APEMC 2022).

@inproceedings{9229191fa12245949196a38f26b6a283,

title = "Cascading Neural Network Blocks of Transistor Level Transceiver Models",

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.",

keywords = "Transceiver modeling, channel simulation, feed-forward neural net-work, signal integrity",

author = "Yixuan Zhao and Hanzhi Ma and Andreas Cangellaris and Li, {Er Ping} and Schutt-Ain{\'e}, {Jos{\'e} E.}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 13th Asia-Pacific International Symposium on Electromagnetic Compatibility and Technical Exhibition, APEMC 2022 ; Conference date: 01-09-2022 Through 04-09-2022",

year = "2022",

doi = "10.1109/APEMC53576.2022.9888478",

language = "English (US)",

series = "2022 Asia-Pacific International Symposium on Electromagnetic Compatibility, APEMC 2022",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "7--9",

booktitle = "2022 Asia-Pacific International Symposium on Electromagnetic Compatibility, APEMC 2022",

address = "United States",

}

TY - GEN

T1 - Cascading Neural Network Blocks of Transistor Level Transceiver Models

AU - Zhao, Yixuan

AU - Ma, Hanzhi

AU - Cangellaris, Andreas

AU - Li, Er Ping

AU - Schutt-Ainé, José E.

PY - 2022

Y1 - 2022

N2 - 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.

AB - 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.

KW - Transceiver modeling

KW - channel simulation

KW - feed-forward neural net-work

KW - signal integrity

UR - http://www.scopus.com/inward/record.url?scp=85139480165&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85139480165&partnerID=8YFLogxK

U2 - 10.1109/APEMC53576.2022.9888478

DO - 10.1109/APEMC53576.2022.9888478

M3 - Conference contribution

AN - SCOPUS:85139480165

T3 - 2022 Asia-Pacific International Symposium on Electromagnetic Compatibility, APEMC 2022

SP - 7

EP - 9

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

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 13th Asia-Pacific International Symposium on Electromagnetic Compatibility and Technical Exhibition, APEMC 2022

Y2 - 1 September 2022 through 4 September 2022

ER -

Cascading Neural Network Blocks of Transistor Level Transceiver Models

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this