Harnessing Photon Indistinguishability in Quantum Extreme Learning Machines

TL;DR

This paper demonstrates how indistinguishable photons can enhance quantum extreme learning machines by increasing feature space dimensionality, leading to improved image classification performance and a quantum advantage.

Contribution

It introduces a novel QELM protocol using indistinguishable photons and multimode fiber, showing experimental and simulated quantum advantages in machine learning tasks.

Findings

Indistinguishable photons improve classification accuracy.

Quantum advantage increases with photon number.

Enhanced feature space dimensionality correlates with performance.

Abstract

Recent advancements in machine learning have led to an exponential increase in computational demands, driving the need for innovative computing platforms. Quantum computing, with its Hilbert space scaling exponentially with the number of particles, emerges as a promising solution. In this work, we implement a quantum extreme machine learning (QELM) protocol leveraging indistinguishable photon pairs and multimode fiber as a random densly connected layer. We experimentally study QELM performance based on photon coincidences -- for distinguishable and indistinguishable photons -- on an image classification task. Simulations further show that increasing the number of photons reveals a clear quantum advantage. We relate this improved performance to the enhanced dimensionality and expressivity of the feature space, as indicated by the increased rank of the feature matrix in both experiment and simulation.