Quantum Optical Neuron for Image Classification via Multiphoton Interference

TL;DR

This paper demonstrates a quantum optical image classifier using Hong-Ou-Mandel interference, enabling energy-efficient, camera-free inference directly at the measurement layer with robustness to noise and resolution.

Contribution

It introduces a novel quantum optical neuron and shallow network that perform image classification via two-photon interference, bypassing pixel-based imaging.

Findings

Achieved high accuracy on benchmark datasets with quantum optical methods.

Demonstrated robustness to experimental noise and input resolution.

Showed potential for applications in low-signal and photon-starved imaging.

Abstract

The rapid growth of machine learning is increasingly constrained by the energy and bandwidth limits of classical hardware. Optical and quantum technologies offer an alternative route, enabling high-dimensional, parallel information processing directly in the physical layer, particularly suited for imaging tasks. In this context, quantum photonic platforms provide both a natural mechanism for computing inner products and a promising path to energy-efficient inference in photon-limited regimes. Here, we experimentally demonstrate a camera-free quantum-optical images classifier that performs inference directly at the measurement layer using Hong-Ou-Mandel (HOM) interference of spatially programmable single photons. Two-photon coincidences directly report the overlap between an input image mode and a learned template, replacing pixel-resolved acquisition with a single global measurement. We realize both a single-perceptron quantum optical neuron and a two-neuron shallow network, achieving high accuracy on benchmark datasets with strong robustness to experimental noise and minimal hardware complexity. With a fixed measurement budget, performance remains insensitive to input resolution, demonstrating intrinsic robustness to the number of pixels, which would be impossible in a classical framework. This approach paves the way toward neuromorphic quantum photonic processors capable of extracting task-relevant information directly from HOM interference, with promising applications in remote object recognition, low-signal sensing, and photon-starved biological microscopy.