Dresden 2026 – scientific programme
Parts | Days | Selection | Search | Updates | Downloads | Help
QI: Fachverband Quanteninformation
QI 10: Quantum Information: Concepts and Methods I
QI 10.6: Talk
Wednesday, March 11, 2026, 10:45–11:00, BEY/0137
Use of Neural Networks to Reconstruct Information on NV-Center Spin Registers — •Alessia Camuti Borani1, Matthias Müller2, and Tommaso Calarco1, 2, 3 — 1Università di Bologna — 2Forschungszentrum Jülich — 3Universität zu Köln
The presentation will focus on the use of Neural Networks to reconstruct information about spin states in NV-center platforms from computational-basis measurement outcomes. Neural Networks can in fact serve as a more efficient alternative to standard reconstruction protocols, thanks to their ability to detect patterns in data.
The quantum platform we simulate consists of the electronic spin of a Nitrogen-Vacancy (NV) defect in diamond, used for initialization and readout, together with the surrounding nuclear carbon spins, which serve as the actual qubits.
In the first part of the talk, we will discuss results on full-state tomography of spin states in NV-center registers using Neural Networks. We will compare the performance obtained when feeding the network with Pauli-basis measurement outcomes to that of a randomized protocol, in which randomly selected gates are applied prior to measurement. In the second part of the talk, we will instead present results on the reconstruction of observables of NV-center systems, rather than full density matrices.
Keywords: Quantum Tomography; Neural Networks; Readout; Quantum Measurements; NV-centers