Photonic quantum generative adversarial networks for classical data - Archive ouverte HAL
Article Dans Une Revue Optica Quantum Année : 2024

Photonic quantum generative adversarial networks for classical data

Tigran Sedrakyan
Alexia Salavrakos

Résumé

In generative learning, models are trained to produce new samples that follow the distribution of the target data. These models were historically difficult to train, until proposals such as generative adversarial networks (GANs) emerged, where a generative and a discriminative model compete against each other in a minimax game. Quantum versions of the algorithm have since been designed for the generation of both classical and quantum data. While most work so far has focused on qubit-based architectures, in this article we present a quantum GAN based on linear optical circuits and Fock-space encoding, which makes it compatible with near-term photonic quantum computing. We demonstrate that the model can learn to generate images by training the model end-to-end experimentally on a single-photon quantum processor.
Fichier principal
Vignette du fichier
opticaq-2-6-458.pdf (3.44 Mo) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04828031 , version 1 (17-12-2024)
hal-04828031 , version 2 (17-12-2024)

Licence

Identifiants

Citer

Tigran Sedrakyan, Alexia Salavrakos. Photonic quantum generative adversarial networks for classical data. Optica Quantum, 2024, 2 (6), pp.458-467. ⟨10.1364/OPTICAQ.530346⟩. ⟨hal-04828031v2⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More