Bayesian Optimization for Stack-Up Design

Abstract

Black-box function optimization is a challenging problem worldwide. Bayesian Optimization is a powerful method used to handle the optimization of functions, which are usually too costly for evaluation. Non-convex black-box function optimization arises in many applied problems. One example of such kind of problems is the PCB stack-up design. With its various covariance functions and different values of hyper-parameters Bayesian Optimization is applied for five-dimensional stack-up design optimization. The results obtained using the Bayesian Optimization are compared with results of other methods.

Meeting Name

2019 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2019 (2019: Jul. 22-26, New Orleans, LA)

Department(s)

Electrical and Computer Engineering

Research Center/Lab(s)

Electromagnetic Compatibility (EMC) Laboratory

Comments

This paper is based upon work supported partially by the National Science Foundation under Grant No. IIP-1440110.

Keywords and Phrases

Bayesian Optimization; Gaussian Process; PCB Stack-Up Design

International Standard Book Number (ISBN)

978-153869199-1

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 2019 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Publication Date

01 Jul 2019

Share

 
COinS