Modeling and benchmarking quantum optical neurons for efficient neural computation
This work addresses the need for energy-efficient neural computation components, potentially benefiting quantum-inspired and hybrid photonic-electronic systems, but it is incremental as it builds on existing theoretical proposals.
The authors tackled the problem of designing quantum optical neurons (QONs) for efficient neural computation by introducing architectures based on interferometers with different photon modulation strategies, achieving performance comparable to classical neurons on MNIST and FashionMNIST datasets, with some configurations showing faster or more stable convergence.
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 modules in software. 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. Our experiments show that two configurations -- HOM-based amplitude modulation and MZ-based phase-shifted modulation -- achieve performance comparable to that of classical neurons in several settings, and in some cases exhibit faster or more stable convergence. In contrast, intensity-based encodings display greater sensitivity to distributional shifts and training instabilities. These results highlight the potential of QONs as efficient and scalable components for future quantum-inspired neural architectures and hybrid photonic-electronic systems.