In this paper, we introduce the design approach of integrated photonic devices by employing reinforcement learning known as attractor selection (AttSel). Here, we combined 3D FDTD with AttSel algorithm, which is based on artificial neural networks, to achieve ultra-compact and highly efficient wavelength demultiplexers with low crosstalk such as. The presented devices consist of SOI materials, which are compatible with complementary MOS technology. Consequently, the reinforcement learning is successfully applied to design smaller and superior integrated photonic devices.
Keyword: inverse design; machine learning; wavelength demultiplexing
Publication Name (dc.title) | Machine learning enabled the design of compact and efficient wavelength demultiplexing photonic devices |
Author/s (dc.contributor.yazarlar) | M. Turduev, E. Bor, O. Alparslan, Y.S. Hanay, H. Kurt, S. Arakawa, M. Murata |
Publication type (dc.type) | Konferans Bildirisi |
Language (dc.language) | İngilizce |
Publication year (dc.date.issued) | 2023 |
National/International (dc.identifier.ulusaluluslararasi) | Uluslararası |
Source (dc.relation.journal) | 2023 IEEE Photonics Conference (IPC) |
Additional source name / Conference information (dc.identifier.kaynakadiekbilgi) | 2023 IEEE Photonics Conference, IPC 2023.- 12-16 November 2023.- Orlando, Florida, USA.- Kod 195842 |
ISSN/ISBN (dc.identifier.issn) | ISBN: 979-8-3503-4722-7; Online ISSN: 2575-274X |
Publisher (dc.publisher) | IEEE Xplore Digital Librar, USA |
Databases (dc.contributor.veritaban) | Web of Science Core Collection |
Databases (dc.contributor.veritaban) | IEEE Xplore |
Databases (dc.contributor.veritaban) | Scopus |
Index Type (dc.identifier.index) | Scopus |
Index Type (dc.identifier.index) | CPCI-S |
Abstract (dc.description.abstract) | In this paper, we introduce the design approach of integrated photonic devices by employing reinforcement learning known as attractor selection (AttSel). Here, we combined 3D FDTD with AttSel algorithm, which is based on artificial neural networks, to achieve ultra-compact and highly efficient wavelength demultiplexers with low crosstalk such as. The presented devices consist of SOI materials, which are compatible with complementary MOS technology. Consequently, the reinforcement learning is successfully applied to design smaller and superior integrated photonic devices. |
Abstract (dc.description.abstract) | Keyword: inverse design; machine learning; wavelength demultiplexing |
URL (dc.rights) | https://ieeexplore.ieee.org/document/10360715 |
DOI (dc.identifier.doi) | 10.1109/IPC57732.2023.10360715 |
Faculty / Institute (dc.identifier.fakulte) | Mühendislik Fakültesi |
Department (dc.identifier.bolum) | Elektrik-Elektronik Mühendisliği Bölümü |
Author(s) in the Institution (dc.contributor.author) | Mirbek TURDUEV |
Kayıt No (dc.identifier.kayitno) | BL9D329BD7 |
Record Add Date (dc.date.available) | 2024-01-25 |
Notes (Publication year) (dc.identifier.notyayinyili) | 2023 |
Wos No (dc.identifier.wos) | WOS:001156890300208 |
Subject Headings (dc.subject) | inverse design |
Subject Headings (dc.subject) | machine learning |
Subject Headings (dc.subject) | wavelength demultiplexing |