Harnessing Photon Indistinguishability in Quantum Extreme Learning Machines

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.

Malo Joly, Adrian Makowski, Baptiste Courme, Lukas Porstendorfer, Steffen Wilksen, Edoardo Charbon, Christopher Gies, Hugo Defienne, Sylvain Gigan (1) __INSTITUTION_9__ Laboratoire Kastler Brossel, (2) Institute of Experimental Physics of Warsaw, (3) Institute for Theoretical Physics of Bremen, (4) Institute for Physics Oldenburg __INSTITUTION_13__ Advanced Quantum Architecture Laboratory Lausanne, (6) Institut des NanoSciences de Paris) · 2025