Modeling and benchmarking quantum optical neurons for efficient neural computation

Abstract

Quantum optical neurons (QONs) are emerging as promising computational units that leverage photonic interference to perform neural operations in an energy-efficient and physically grounded manner. Building on recent theoretical proposals, we introduce a family of QON architectures based on Hong-Ou-Mandel (HOM) and Mach-Zehnder (MZ) interferometers, incorporating different photon modulation strategies -- phase, amplitude, and intensity. These physical setups yield distinct pre-activation functions, which we implement as fully differentiable software modules. We evaluate these QONs both in isolation and as building blocks of multilayer networks, training them on binary and multiclass image classification tasks using the MNIST and FashionMNIST datasets. Each experiment is repeated over five independent runs and assessed under both ideal and non-ideal conditions to measure accuracy, convergence, and robustness. Across settings, MZ-based neurons exhibit consistently stable behavior -- including under noise -- while HOM amplitude modulation performs competitively in deeper architectures, in several cases approaching classical performance. In contrast, phase- and intensity-modulated HOM-based variants show reduced stability and greater sensitivity to perturbations. These results highlight the potential of QONs as efficient and scalable components for future quantum-inspired neural architectures and hybrid photonic-electronic systems. The code is publicly available at https://github.com/gvessio/quantum-optical-neurons.

References in corpus (24)

• Quantum Machine Learning
• Decoherence, einselection, and the quantum origins of the classical
• All-Optical Machine Learning Using Diffractive Deep Neural Networks
• Supervised learning with quantum enhanced feature spaces
• Kernel methods in machine learning
• Superconducting nanowire single-photon detectors: physics and applications
• All Optical Neural Network with Nonlinear Activation Functions
• Impact of ionizing radiation on superconducting qubit coherence
• Entanglement-Based Machine Learning on a Quantum Computer
• Two-photon interference: the Hong-Ou-Mandel effect
• Attosecond-Resolution Hong-Ou-Mandel Interferometry
• Interferometric visibility and coherence
• Quantum Decoherence of Single-Photon Counters
• Experimental quantum kernel machine learning with nuclear spins in a solid
• Evaluating Performance of Photon-Number-Resolving Detectors
• Classical analog of qubit logic based on a magnon Bose-Einstein condensate
• Quantum-enhanced pattern recognition
• A high visibility Hong-Ou-Mandel interference via a time-resolved coincidence measurement
• Experimental realization of a quantum image classifier via tensor-network-based machine learning
• Estimation with ultimate quantum precision of the transverse displacement between two photons via two-photon interference sampling measurements
• Two-photon interferences of weak coherent lights
• Normalized multi-pion Hanbury Brown and Twiss correlation functions of pion-emitting sources with Bose-Einstein condensation
• Quantum Kernel Evaluation via Hong-Ou-Mandel Interference
• Quantum optical classifier with superexponential speedup