Publication:

Deep-Learning-Enabled Inverse Design of Electromagnetic Structures

datacite.rightsrestricted
dc.contributor.advisorSengupta, Kaushik
dc.contributor.authorFisher, Sebastian
dc.date.accessioned2024-07-03T13:55:18Z
dc.date.accessioned2026-09-29T22:36:32Z
dc.date.available2024-07-03T13:55:18Z
dc.date.available2026-09-29T22:36:32Z
dc.date.created2024-04-15
dc.date.issued2024-07-03
dc.description.abstractThe design of electromagnetic (EM) structures and their co-design with related circuits plays an important role in the development of high-frequency circuits and systems. Current design methodologies rely on a bottom-up approach to build electromagnetic structures out of a set of structures whose function is known previously, such as transmission lines. This thesis discusses the use of deep learning to enable a top-down approach to design of EM structures, known as inverse design, where structures are synthesized from a set of desired operating parameters. This has the potential to greatly speed up EM structure design, as well as to find designs closer to the overall optimal in the design space. In this thesis, a tandem neural network approach is used for inverse synthesis of matching networks, a type of EM structure. Tandem neural networks have been shown to be effective in previous works on inverse design for other applications. The work here also serves as a first step in the creation of an integrated codebase/tool for EM structure and circuit co-design in the industry standard Cadence Virtuoso software using the Python programming language.en_US
dc.format.mimetypeapplication/pdf
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/dsp017s75dg70p
dc.identifier.urihttps://theses-dissertations.princeton.edu/handle/88435/dsp017s75dg70p
dc.language.isoenen_US
dc.titleDeep-Learning-Enabled Inverse Design of Electromagnetic Structuresen_US
dc.typePrinceton University Senior Theses
dspace.entity.typePublication
pu.contributor.authorid920227765
pu.date.classyear2024en_US
pu.departmentElectrical and Computer Engineeringen_US
pu.mudd.walkinNoen_US
pu.pdf.coverpageSeniorThesisCoverPage

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
FISHER-SEBASTIAN-THESIS.pdf
Size:
9.08 MB
Format:
Adobe Portable Document Format
Download

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
LICENSE.txt
Size:
253 B
Format:
Plain Text
Description:
Download