Photonic classification on a single diffractive layer

TL;DR

This paper introduces a highly efficient optical classification method using a single diffractive layer and a spatial light modulator, achieving over 90% accuracy in noisy conditions, simplifying photonic neural networks.

Contribution

The study presents a novel single-layer diffractive optical classifier that reduces complexity and cost while maintaining high accuracy, advancing photonic neural network deployment.

Findings

Achieves over 90% accuracy in noisy road sign classification.

Uses a single diffractive layer with a spatial light modulator for optical classification.

Demonstrates fast, light-speed image classification with a simple linear classifier.

Abstract

Photonic computation started to shape the future of fast, efficient and accessible computation. The advantages brought by light based Diffractive Deep Neural Networks (D2NN), are shown to be overwhelmingly advantageous especially in targeting classification problems. However, cost and complexity of multi-layer systems are the main challenges that reduce the deployment of this technology. In this study, we develop a simple yet extremely efficient way to achieve optical classification using a single diffractive optical layer. A spatial light modulator is used not only to emulate the classifying system but also the input medium. We show that using a simple interpretable linear classifier, images can be classified at the speed of light. We perform classification of road signs under the effect of noise and demonstrate that we can successfully classify input images with more than 90% accuracy even with 13% noise/imperfection.