English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT

Released

Journal Article

Deep Learning of Quantum Many-Body Dynamics via Random Driving

MPS-Authors
/persons/resource/persons300396

Mohseni,  Naeimeh
Marquardt Division, Max Planck Institute for the Science of Light, Max Planck Society;

/persons/resource/persons216883

Fösel,  Thomas
Marquardt Division, Max Planck Institute for the Science of Light, Max Planck Society;
Friedrich-Alexander-Universität Erlangen-Nürnberg, External Organizations;

/persons/resource/persons226776

Guo,  Lingzhen
Marquardt Division, Max Planck Institute for the Science of Light, Max Planck Society;

/persons/resource/persons61068

Navarrete-Benlloch,  Carlos
Marquardt Division, Max Planck Institute for the Science of Light, Max Planck Society;
Wilczek Quantum Center, School of Physics and Astronomy,Shanghai Jiao Tong University;
Shanghai Research Center for Quantum Sciences;

/persons/resource/persons201125

Marquardt,  Florian
Marquardt Division, Max Planck Institute for the Science of Light, Max Planck Society;
Friedrich-Alexander-Universität Erlangen-Nürnberg, External Organizations;

External Resource
No external resources are shared
Fulltext (restricted access)
There are currently no full texts shared for your IP range.
Fulltext (public)

q-2022-05-17-714.pdf
(Publisher version), 6MB

Supplementary Material (public)

2021_DeepLearning_NM.png
(Supplementary material), 66KB

Citation

Mohseni, N., Fösel, T., Guo, L., Navarrete-Benlloch, C., & Marquardt, F. (2022). Deep Learning of Quantum Many-Body Dynamics via Random Driving. Quantum, (6), 714. doi:10.22331/q-2022-05-17-714.


Cite as: https://hdl.handle.net/21.11116/0000-0008-7E64-B
Abstract
Neural networks have emerged as a powerful way to approach many practical problems in quantumphysics. In this work, we illustrate the power of deep learning to predict the dynamics of a quantummany-body system, where the training is based purely on monitoring expectation values of observables under random driving. The trained recurrent network is able to produce accurate predictions for driving trajectories entirely different than those observed during training. As a proof of principle, here we train the network on numerical data generated from spin models, showing that it can learn the dynamics of observables of interest without needing information about the full quantum state.This allows our approach to be applied eventually to actual experimental data generated from aquantum many-body system that might be open, noisy, or disordered, without any need for a detailedunderstanding of the system. This scheme provides considerable speedup for rapid explorations andpulse optimization. Remarkably, we show the network is able to extrapolate the dynamics to times longer than those it has been trained on, as well as to the infinite-system-size limit.