Presentation
17 March 2023 A Clements-type silicon photonics 16x16 analog matrix processor with complex-valued inputs toward nanophotonics accelerators
Author Affiliations +
Proceedings Volume PC12438, AI and Optical Data Sciences IV; PC1243802 (2023) https://doi.org/10.1117/12.2648549
Event: SPIE OPTO, 2023, San Francisco, California, United States
Abstract
We show our recent progress on a Clements-type16x16 on-chip matrix processor based on silicon photonics and a new type of electro-optic digital-to-analog converters (EO DACs) with a higher signal-to-noise ratio. For the former, we developed a machine-learning-based calibration technique that involves theoretical modeling with circuit parameters (loss, phase error, splitting ratio, and crosstalks), which is adequate to obtain better fidelity for large-scale imperfect interferometers. After the calibration, we demonstrated a 16x16 identity matrix and several permutation matrices with a high signal-to-noise ratio and a well-known MNIST database classification task. For the latter, we developed low-loss and wavelength insensitive EO DACs consisting of 1:1 Y splitters and phase modulators that are useful for DAC-less input units for photonic accelerators.
Conference Presentation
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Shota Kita, Kohei Ikeda, Kengo Nozaki, Kenta Takata, Kazuo Aoyama, Keijiro Suzuki, Yuriko Maegami, Morifumi Ohno, Guangwei Cong, Noritsugu Yamamoto, Koji Yamamoto, Akihiko Shinya, Hiroshi Sawada, and Masaya Notomi "A Clements-type silicon photonics 16x16 analog matrix processor with complex-valued inputs toward nanophotonics accelerators", Proc. SPIE PC12438, AI and Optical Data Sciences IV, PC1243802 (17 March 2023); https://doi.org/10.1117/12.2648549
Advertisement
Advertisement
KEYWORDS
Silicon photonics

Analog electronics

Nanophotonics

Phase shifts

Calibration

Machine learning

Matrices

Back to Top