Optical machine learning with incoherent light and a single-pixel detector

TL;DR

This paper introduces an optical machine learning framework using single-pixel imaging that performs pattern recognition under incoherent light, reducing complexity and enhancing programmability compared to traditional diffractive neural networks.

Contribution

The proposed MLSPI system enables optical pattern recognition with incoherent light, lowering experimental complexity and improving programmability over existing coherent-light DNNs.

Findings

Operates under incoherent lighting conditions

Reduces experimental complexity

Easily programmable

Abstract

An optical diffractive neural network (DNN) can be implemented with a cascaded phase mask architecture. Like an optical computer, the system can perform machine learning tasks such as number digit recognition in an all-optical manner. However, the system can only work under coherent light illumination and the precision requirement in practical experiments is quite high. This paper proposes an optical machine learning framework based on single-pixel imaging (MLSPI). The MLSPI system can perform the same linear pattern recognition task as DNN. Furthermore, it can work under incoherent lighting conditions, has lower experimental complexity and can be easily programmable.