Phase-Change Photonic Memory for Optical Neural Networks with Nanoseconds in-Situ Training Capability
Electrically programmable photonic memory based on <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{Sb}_{2} \text{Se}_{3}$</tex> integrated with PIN-diode silicon waveguide heaters were proposed and fabricated. The novel memory devices allow fast in-situ training and zero-static-power-consumption data processing in optical neural networks.
Authors
- W. B. Wang (ORCID: https://orcid.org/0009-0005-8718-1856)
- Hongtao Lin (ORCID: https://orcid.org/0000-0001-7432-3644)
- Lan Li (ORCID: https://orcid.org/0000-0002-9097-9157)
- Bo Tang (ORCID: https://orcid.org/0000-0002-8712-7025)
- Junying Li (ORCID: https://orcid.org/0000-0003-0405-9352)
- Yiting Yun
- Maoliang Wei (ORCID: https://orcid.org/0009-0001-6965-8180)
- Kai Xu (ORCID: https://orcid.org/0000-0003-2210-046X)
Institutions
- Chinese Academy of Sciences (CN)
- Westlake University (CN)
- Institute of Microelectronics (CN)
- Zhejiang Lab (CN)
- University of Chinese Academy of Sciences (CN)
Publication Details
- Published
- 2025-06-29
- DOI
- https://doi.org/10.23919/oecc/psc62146.2025.11111583
- Primary Topic
- Neural Networks and Reservoir Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Institute of Microelectronics of the Chinese Academy of Sciences
- National Key Research and Development Program of China