We present and experimentally evaluate using transfer learning to address experimental data scarcity when training neural network (NN) models for Mach-Zehnder interferometer mesh-based optical matrix multipliers. Our approach involves pre-training the model using synthetic data generated from a less accurate analytical model and fine-tuning with experimental data. Our investigation demonstrates that this method yields significant reductions in modeling errors compared to using an analytical model, or a standalone NN model when training data is limited. Utilizing regularization techniques and ensemble averaging, we achieve < 1 dB root-mean-square error on the matrix weights implemented by a 3x3 photonic chip while using only 25% of the available data.
@article{arxiv.2308.11630,
title = {Addressing Data Scarcity in Optical Matrix Multiplier Modeling Using Transfer Learning},
author = {Ali Cem and Ognjen Jovanovic and Siqi Yan and Yunhong Ding and Darko Zibar and Francesco Da Ros},
journal= {arXiv preprint arXiv:2308.11630},
year = {2023}
}