Supervised learning of the Jaynes–Cummings Hamiltonian

Abstract We investigate the utility of deep neural networks (DNNs) in estimating the Jaynes-Cummings Hamiltonian’s parameters from its energy spectrum alone. We assume that the energy spectrum may or may not be corrupted by noise. In the noiseless case, we use the vanilla DNN (vDNN) model and find t...

Full description

Saved in:
Bibliographic Details
Main Authors: Woohyun Choi, Chang-Woo Lee, Changsuk Noh
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-02611-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849763877274779648
author Woohyun Choi
Chang-Woo Lee
Changsuk Noh
author_facet Woohyun Choi
Chang-Woo Lee
Changsuk Noh
author_sort Woohyun Choi
collection DOAJ
description Abstract We investigate the utility of deep neural networks (DNNs) in estimating the Jaynes-Cummings Hamiltonian’s parameters from its energy spectrum alone. We assume that the energy spectrum may or may not be corrupted by noise. In the noiseless case, we use the vanilla DNN (vDNN) model and find that the error tends to decrease as the number of input nodes increases. The best-achieved root mean squared error is of the order of $$10^{-5}$$ . The vDNN model, trained on noiseless data, demonstrates resilience to Gaussian noise, but only up to a certain extent. To cope with this issue, we employ a denoising U-Net and combine it with the vDNN to find that the new model reduces the error by up to about 77%. Our study exemplifies that deep learning models can help estimate the parameters of a Hamiltonian even when the data is corrupted by noise.
format Article
id doaj-art-3cd14c6147d849f4b8f93b18dfb2f483
institution DOAJ
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-3cd14c6147d849f4b8f93b18dfb2f4832025-08-20T03:05:17ZengNature PortfolioScientific Reports2045-23222025-07-0115111110.1038/s41598-025-02611-wSupervised learning of the Jaynes–Cummings HamiltonianWoohyun Choi0Chang-Woo Lee1Changsuk Noh2Kyungpook National UniversityKorea Institute for Advanced StudyKyungpook National UniversityAbstract We investigate the utility of deep neural networks (DNNs) in estimating the Jaynes-Cummings Hamiltonian’s parameters from its energy spectrum alone. We assume that the energy spectrum may or may not be corrupted by noise. In the noiseless case, we use the vanilla DNN (vDNN) model and find that the error tends to decrease as the number of input nodes increases. The best-achieved root mean squared error is of the order of $$10^{-5}$$ . The vDNN model, trained on noiseless data, demonstrates resilience to Gaussian noise, but only up to a certain extent. To cope with this issue, we employ a denoising U-Net and combine it with the vDNN to find that the new model reduces the error by up to about 77%. Our study exemplifies that deep learning models can help estimate the parameters of a Hamiltonian even when the data is corrupted by noise.https://doi.org/10.1038/s41598-025-02611-w
spellingShingle Woohyun Choi
Chang-Woo Lee
Changsuk Noh
Supervised learning of the Jaynes–Cummings Hamiltonian
Scientific Reports
title Supervised learning of the Jaynes–Cummings Hamiltonian
title_full Supervised learning of the Jaynes–Cummings Hamiltonian
title_fullStr Supervised learning of the Jaynes–Cummings Hamiltonian
title_full_unstemmed Supervised learning of the Jaynes–Cummings Hamiltonian
title_short Supervised learning of the Jaynes–Cummings Hamiltonian
title_sort supervised learning of the jaynes cummings hamiltonian
url https://doi.org/10.1038/s41598-025-02611-w
work_keys_str_mv AT woohyunchoi supervisedlearningofthejaynescummingshamiltonian
AT changwoolee supervisedlearningofthejaynescummingshamiltonian
AT changsuknoh supervisedlearningofthejaynescummingshamiltonian