Data-efficient Modeling of Optical Matrix Multipliers Using Transfer Learning

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.

cs.LG cs.ET cs.NE Physics Engineering Computer Science

View graph Source

Paper

References (8)

01Fiber-Agnostic Machine Learning-Based Raman Amplifier ModelsU. C. de Moura, D. Zibar, A. M. R. Brusin et al.2023 · Journal of Lightwave Technology · 28 citations

02Photonics for artificial intelligence and neuromorphic computingB. Shastri, A. Tait, T. F. D. Lima et al.2020 · Nature Photonics · 1.7k citations In Library

03Control and Calibration Recipes for Photonic Integrated CircuitsM. Milanizadeh, A. Melloni, Sara Ahmadi et al.2020 · IEEE Journal of Selected Topics in Quantum Electronics · 42 citations

04Canceling Thermal Cross-Talk Effects in Photonic Integrated CircuitsM. Milanizadeh, D. Aguiar, A. Melloni et al.2019 · Journal of Lightwave Technology · 104 citations

05Deep learning with coherent nanophotonic circuitsYichen Shen, N. Harris, S. Skirlo et al.2016 · Nature Photonics · 3.0k citations In Library

06Reconfigurable SDM Switching Using Novel Silicon Photonic Integrated CircuitYunhong Ding, V. Kamchevska, K. Dalgaard et al.2016 · Scientific Reports · 58 citations

07Data-driven Modeling of MZI-based Optical Matrix Multipliers,2022

08Efficient On-Chip Training of Optical NNs Using Genetic Algorithm,2021 · ACS Photonics

Similar papers

Data-efficient Modeling of Optical Matrix Multipliers Using Transfer LearningAli Cem, Ognjen Jovanovic, Sinian Yan et al.2023 In Library

Addressing data scarcity in optical matrix multiplier modeling using transfer learningAli Cem, Ognjen Jovanovic, Siqi Yan et al.2023 · Optics Letters In Library

Addressing Data Scarcity in Optical Matrix Multiplier Modeling Using Transfer LearningAli Cem, Ognjen Jovanovic, Siqi Yan et al.2023 · arXiv (Cornell University) · 3 citations In Library

Modeling of Optical Matrix Multipliers Using Transposed Convolutional Neural NetworksAli Cem, Siqi Yan, Uiara Celine de Moura et al.2022 · 2022 IEEE Photonics Conference (IPC) In Library

Data-Driven Modeling of Mach-Zehnder Interferometer-Based Optical Matrix MultipliersAli Cem, Siqi Yan, Yunhong Ding et al.2023 · Journal of Lightwave Technology In Library

Data-driven Modeling of Mach-Zehnder Interferometer-based Optical Matrix MultipliersAli Cem, Siqi Yan, Yunhong Ding et al.2022 · arXiv (Cornell University) In Library

Comparison of Models for Training Optical Matrix Multipliers in Neuromorphic PICsAli Cem, Shaomin Yan, Uiara Celine de Moura et al.2022 In Library

Comparison of Models for Training Optical Matrix Multipliers in Neuromorphic PICsAli Cem, Siqi Yan, Uiara Celine de Moura et al.2021 · arXiv (Cornell University) In Library

Machine learning for photonics: from computing to communicationFrancesco Da Ros, Ali Cem, Yevhenii Osadchuk et al.2023 In Library

Real-Valued Optical Matrix Computing with Simplified MZI MeshBo Wu, Shaojie Liu, Junwei Cheng et al.2023 · Intelligent Computing In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal