Machine learning-based classification of vector vortex beams

TL;DR

This paper presents a novel machine learning approach, using CNNs and PCA, for classifying complex vector vortex beams, enhancing the analysis of structured light in quantum optics.

Contribution

It introduces a flexible experimental platform for generating vector vortex beams and applies machine learning techniques for their classification, advancing high-dimensional quantum resource analysis.

Findings

Machine learning improves classification accuracy of vortex beams.

CNNs and PCA effectively recognize polarization patterns.

Enhanced characterization of structured light for quantum applications.

Abstract

Structured light is attracting significant attention for its diverse applications in both classical and quantum optics. The so-called vector vortex beams display peculiar properties in both contexts due to the non-trivial correlations between optical polarization and orbital angular momentum. Here we demonstrate a new, flexible experimental approach to the classification of vortex vector beams. We first describe a platform for generating arbitrary complex vector vortex beams inspired to photonic quantum walks. We then exploit recent machine learning methods -- namely convolutional neural networks and principal component analysis -- to recognize and classify specific polarization patterns. Our study demonstrates the significant advantages resulting from the use of machine learning-based protocols for the construction and characterization of high-dimensional resources for quantum protocols.