Data-efficient Modeling of Optical Matrix Multipliers Using Transfer Learning

2022/11/29 by Ali Cem, Ognjen Jovanovic, Cem, Ali +9
Computer Science · Engineering · #Emerging Technologies (cs.ET) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Reservoir Computing #Neural and Evolutionary Computing (cs.NE) #Optical Network Technologies #Photonic and Optical Devices

paper · pdf · doi:10.48550/arxiv.2211.16038

openalex publication_date 2022/11/29 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Related

• Addressing Data Scarcity in Optical Matrix Multiplier Modeling Using Transfer Learning
• Data-driven Modeling of Mach-Zehnder Interferometer-based Optical Matrix Multipliers
• Comparison of Models for Training Optical Matrix Multipliers in Neuromorphic PICs
• Experimental Demonstration of Imperfection-Agnostic Local Learning Rules on Photonic Neural Networks with Mach-Zehnder Interferometric Meshes
• Acceleration Method for Learning Fine-Layered Optical Neural Networks