Leveraging Multiplexed Metasurfaces for Multi-Task Learning with All-Optical Diffractive Processors

TL;DR

This paper presents a novel all-optical multi-task neural network using multiplexed metasurfaces that can classify multiple datasets simultaneously with high accuracy, leveraging polarization and wavelength multiplexing for efficient optical computation.

Contribution

It introduces a dual-channel and three-task multiplexed diffractive neural network using metasurfaces, with a new end-to-end optimization framework for improved multi-task optical classification.

Findings

Achieved over 80% accuracy in three-task classification.

Demonstrated performance comparable to single-task neural networks.

Extended the approach to multi-task recognition with satisfactory results.

Abstract

Diffractive Neural Networks (DNNs) leverage the power of light to enhance computational performance in machine learning, offering a pathway to high-speed, low-energy, and large-scale neural information processing. However, most existing DNN architectures are optimized for single tasks and thus lack the flexibility required for the simultaneous execution of multiple tasks within a unified artificial intelligence platform. In this work, we utilize the polarization and wavelength degrees of freedom of light to achieve optical multi-task identification using the MNIST, FMNIST, and KMNIST datasets. Employing bilayer cascaded metasurfaces, we construct dual-channel DNNs capable of simultaneously classifying two tasks, using polarization and wavelength multiplexing schemes through a meta-atom library. Numerical evaluations demonstrate performance accuracies comparable to those of individually trained single-channel, single-task DNNs. Extending this approach to three-task parallel recognition reveals an expected performance decline yet maintains satisfactory classification accuracies of greater than 80% for all tasks. We further introduce a novel end-to-end joint optimization framework to redesign the three-task classifier, demonstrating substantial improvements over the meta-atom library design and offering the potential for future multi-channel DNN designs. Our study could pave the way for the development of ultrathin, high-speed, and high-throughput optical neural computing systems.