We revisit the application of neural networks techniques to quantum state tomography. We confirm that the positivity constraint can be successfully implemented with trained networks that convert outputs from standard feed-forward neural networks to valid descriptions of quantum states. Any standard neural-network architecture can be adapted with our method. Our results open possibilities to use state-of-the-art deep-learning methods for quantum state reconstruction under various types of noise.
@article{arxiv.2206.06736,
title = {Neural-network quantum state tomography},
author = {D. Koutny and L. Motka and Z. Hradil and J. Rehacek and L. L. Sanchez-Soto},
journal= {arXiv preprint arXiv:2206.06736},
year = {2022}
}
Comments
8 pages, 4 color figures. Comments are most welcome