Bayesian active learning for multi‐objective feasible region identification in microwave devices

In microwave device and circuit design, many simulations are often needed to find a set of designs that satisfy one or multiple specifications chosen by the designer upfront: the feasible region. A novel Bayesian active learning framework is presented to accurately identify the feasible region with...

Full description

Saved in:

Bibliographic Details
Published in:	Electronics letters 2021-05, Vol.57 (10), p.400-403
Main Authors:	Garbuglia, Federico, Qing, Jixiang, Knudde, Nicolas, Spina, Domenico, Couckuyt, Ivo, Deschrijver, Dirk, Dhaene, Tom
Format:	Article
Language:	eng
Subjects:	Computer-aided circuit analysis and design Electronic engineering computing Machine learning (artificial intelligence) Microwave circuits and devices Other topics in statistics
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	In microwave device and circuit design, many simulations are often needed to find a set of designs that satisfy one or multiple specifications chosen by the designer upfront: the feasible region. A novel Bayesian active learning framework is presented to accurately identify the feasible region with a low number of simulations. The technique leverages on a stochastic model to obtain an efficient and automated procedure. A suitable application example validates the proposed technique and shows its effectiveness to rapidly obtain many suitable designs.
ISSN:	0013-5194 1350-911X