Add to BibSonomyAbstract
We demonstrate transfer learning-assisted neural network models for optical matrix multipliers with scarce measurement data. Our approach uses < 10% of experimental data needed for best performance and outperforms analytical models for a Mach-Zehnder interferometer mesh.
© 2023 The Author(s)
PDF ArticleMore Like This
Comparison of Models for Training Optical Matrix Multipliers in Neuromorphic PICs
A. Cem, S. Yan, U.C. de Moura, Y. Ding, D. Zibar, and F. Da Ros
M2G.5 Optical Fiber Communication Conference (OFC) 2022
Optimizing Deep Learning Based Retinal Diseases Classification On Optical Coherence Tomography Scans
Aditya Chandra Mandal and Abhijeet Phatak
1263220 European Conference on Biomedical Optics (ECBO) 2023
Transfer Learning-based ROADM EDFA Wavelength Dependent Gain Prediction Using Minimized Data Collection
Zehao Wang, Dan Kilper, and Tingjun Chen
Th2A.1 Optical Fiber Communication Conference (OFC) 2023