Data-efficient Modeling of Optical Matrix Multipliers Using Transfer Learning

11/29/2022

∙

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.

READ FULL TEXT

Data-efficient Modeling of Optical Matrix Multipliers Using Transfer Learning

Data-driven Modeling of Mach-Zehnder Interferometer-based Optical Matrix Multipliers

Self-Normalizing Neural Network, Enabling One Shot Transfer Learning for Modeling EDFA Wavelength Dependent Gain

Learning across label confidence distributions using Filtered Transfer Learning

Comparison of Models for Training Optical Matrix Multipliers in Neuromorphic PICs

Wildfire Detection Via Transfer Learning: A Survey

Transfer Learning-Based Outdoor Position Recovery with Telco Data

Data Efficient Lithography Modeling with Transfer Learning and Active Data Selection

Data-efficient Modeling of Optical Matrix Multipliers Using Transfer Learning

Related Research

Data-driven Modeling of Mach-Zehnder Interferometer-based Optical Matrix Multipliers

Self-Normalizing Neural Network, Enabling One Shot Transfer Learning for Modeling EDFA Wavelength Dependent Gain

Learning across label confidence distributions using Filtered Transfer Learning

Comparison of Models for Training Optical Matrix Multipliers in Neuromorphic PICs

Wildfire Detection Via Transfer Learning: A Survey

Transfer Learning-Based Outdoor Position Recovery with Telco Data

Data Efficient Lithography Modeling with Transfer Learning and Active Data Selection