Addressing data scarcity in optical matrix multiplier modeling using transfer learning

Ali Cem, Ognjen Jovanovic, Siqi Yan, Yunhong Ding, Darko Zibar, Francesco da Ros*

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

2 Downloads (Pure)


We present and experimentally evaluate the use of 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 pretraining the model using synthetic data generated from a less accurate analytical model and fine-tuning it 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 3×3 matrix weights implemented by a photonic chip while using only 25% of the available data.

Original languageEnglish
JournalOptics Letters
Issue number24
Pages (from-to)6553-6556
Publication statusPublished - 15 Dec 2023


Dive into the research topics of 'Addressing data scarcity in optical matrix multiplier modeling using transfer learning'. Together they form a unique fingerprint.

Cite this