2D Spectral Transposed Convolutional Neural Network for S-Parameter Predictions

Yiliang Guo; Xingchen Li; Madhavan Swaminathan

doi:10.1109/EPEPS53828.2022.9947109

2D Spectral Transposed Convolutional Neural Network for S-Parameter Predictions

Yiliang Guo, Xingchen Li, Madhavan Swaminathan

Electrical Engineering

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

2 Citations (SciVal)

Abstract

In packaging problems, S-parameter predictions are necessary. Machine learning methods lead to dimensionality related challenges which we address here through spectral trans-posed convolutional neural network using 2D kernels. Results show that Normalized Mean-squared Error (NMSE) dropped 0.002 by using 53.7% of the parameters.

Original language	English (US)
Title of host publication	EPEPS 2022 - IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665450751
DOIs	https://doi.org/10.1109/EPEPS53828.2022.9947109
State	Published - 2022
Event	31st IEEE Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2022 - San Jose, United States Duration: Oct 9 2022 → Oct 12 2022

Publication series

Name	EPEPS 2022 - IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems

Conference

Conference	31st IEEE Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2022
Country/Territory	United States
City	San Jose
Period	10/9/22 → 10/12/22

All Science Journal Classification (ASJC) codes

Hardware and Architecture
Electrical and Electronic Engineering
Safety, Risk, Reliability and Quality
Electronic, Optical and Magnetic Materials
Instrumentation

Access to Document

10.1109/EPEPS53828.2022.9947109

Cite this

Guo, Y., Li, X., & Swaminathan, M. (2022). 2D Spectral Transposed Convolutional Neural Network for S-Parameter Predictions. In EPEPS 2022 - IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS 2022 - IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EPEPS53828.2022.9947109

Guo, Yiliang ; Li, Xingchen ; Swaminathan, Madhavan. / 2D Spectral Transposed Convolutional Neural Network for S-Parameter Predictions. EPEPS 2022 - IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems. Institute of Electrical and Electronics Engineers Inc., 2022. (EPEPS 2022 - IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems).

@inproceedings{e92f6781696148259b0721166565ddb9,

title = "2D Spectral Transposed Convolutional Neural Network for S-Parameter Predictions",

abstract = "In packaging problems, S-parameter predictions are necessary. Machine learning methods lead to dimensionality related challenges which we address here through spectral trans-posed convolutional neural network using 2D kernels. Results show that Normalized Mean-squared Error (NMSE) dropped 0.002 by using 53.7% of the parameters.",

author = "Yiliang Guo and Xingchen Li and Madhavan Swaminathan",

note = "Funding Information: include optimizing the structure of 2D convolutional layers to accelerate the training time. ACKNOWLEDGMENT This work was supported by DARPA under the Warden program (Project Number GR00013386). Publisher Copyright: {\textcopyright} 2022 IEEE.; 31st IEEE Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2022 ; Conference date: 09-10-2022 Through 12-10-2022",

year = "2022",

doi = "10.1109/EPEPS53828.2022.9947109",

language = "English (US)",

series = "EPEPS 2022 - IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems",

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

booktitle = "EPEPS 2022 - IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems",

address = "United States",

}

Guo, Y, Li, X & Swaminathan, M 2022, 2D Spectral Transposed Convolutional Neural Network for S-Parameter Predictions. in EPEPS 2022 - IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems. EPEPS 2022 - IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems, Institute of Electrical and Electronics Engineers Inc., 31st IEEE Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2022, San Jose, United States, 10/9/22. https://doi.org/10.1109/EPEPS53828.2022.9947109

2D Spectral Transposed Convolutional Neural Network for S-Parameter Predictions. / Guo, Yiliang; Li, Xingchen; Swaminathan, Madhavan.
EPEPS 2022 - IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems. Institute of Electrical and Electronics Engineers Inc., 2022. (EPEPS 2022 - IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems).

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

TY - GEN

T1 - 2D Spectral Transposed Convolutional Neural Network for S-Parameter Predictions

AU - Guo, Yiliang

AU - Li, Xingchen

AU - Swaminathan, Madhavan

N1 - Funding Information: include optimizing the structure of 2D convolutional layers to accelerate the training time. ACKNOWLEDGMENT This work was supported by DARPA under the Warden program (Project Number GR00013386). Publisher Copyright: © 2022 IEEE.

PY - 2022

Y1 - 2022

N2 - In packaging problems, S-parameter predictions are necessary. Machine learning methods lead to dimensionality related challenges which we address here through spectral trans-posed convolutional neural network using 2D kernels. Results show that Normalized Mean-squared Error (NMSE) dropped 0.002 by using 53.7% of the parameters.

AB - In packaging problems, S-parameter predictions are necessary. Machine learning methods lead to dimensionality related challenges which we address here through spectral trans-posed convolutional neural network using 2D kernels. Results show that Normalized Mean-squared Error (NMSE) dropped 0.002 by using 53.7% of the parameters.

UR - http://www.scopus.com/inward/record.url?scp=85143397061&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85143397061&partnerID=8YFLogxK

U2 - 10.1109/EPEPS53828.2022.9947109

DO - 10.1109/EPEPS53828.2022.9947109

M3 - Conference contribution

AN - SCOPUS:85143397061

T3 - EPEPS 2022 - IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems

BT - EPEPS 2022 - IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 31st IEEE Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS 2022

Y2 - 9 October 2022 through 12 October 2022

ER -

Guo Y, Li X, Swaminathan M. 2D Spectral Transposed Convolutional Neural Network for S-Parameter Predictions. In EPEPS 2022 - IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems. Institute of Electrical and Electronics Engineers Inc. 2022. (EPEPS 2022 - IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems). doi: 10.1109/EPEPS53828.2022.9947109

2D Spectral Transposed Convolutional Neural Network for S-Parameter Predictions

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this