AI and the World's Hard Problems · Quantum physics & quantum computing · arXiv · 2026-10-19
Hybrid boson sampling-neural network architecture for enhanced classification
The paper proposes a hybrid framework that combines boson sampling with a neural network to build quantum kernels for support vector machine classification. The neural network maps data features onto a programmable boson sampling circuit, producing high-dimensional quantum states. On four datasets, the model outperformed classical linear and sigmoid kernels.