Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Generation of Bose-Einstein Condensates' Ground State Through Machine Learning.

Xiao Liang1,2, Huan Zhang1,2, Sheng Liu1,2

  • 1Laboratory of Quantum Information, University of Science and Technology of China, Hefei, 230026, China.

Scientific Reports
|November 7, 2018
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A prospective randomized comparison of early embryo cleavage kinetics between two media culture systems.

Pakistan journal of medical sciences·2017
Same author

Transcript profile analysis reveals important roles of jasmonic acid signalling pathway in the response of sweet potato to salt stress.

Scientific reports·2017
Same author

Pnserpin: A Novel Serine Protease Inhibitor from Extremophile Pyrobaculum neutrophilum.

International journal of molecular sciences·2017
Same author

The OsHAPL1-DTH8-Hd1 complex functions as the transcription regulator to repress heading date in rice.

Journal of experimental botany·2017
Same author

Spliced leader-based analyses reveal the effects of polycyclic aromatic hydrocarbons on gene expression in the copepod Pseudodiaptomus poplesia.

Aquatic toxicology (Amsterdam, Netherlands)·2017
Same author

DNA barcoding species in Alexandrium tamarense complex using ITS and proposing designation of five species.

Harmful algae·2017
This summary is machine-generated.

Deep convolutional neural networks can accurately simulate Bose-Einstein condensates ground states. This method precisely predicts wave functions for various potentials, offering a novel simulation approach.

Area of Science:

  • Quantum physics
  • Computational physics
  • Machine learning

Background:

  • Bose-Einstein condensates (BECs) are quantum states of matter with unique properties.
  • Simulating BECs ground states is computationally intensive.
  • The Gross-Pitaevskii equation (GPE) describes BECs but requires significant computational resources.

Purpose of the Study:

  • To investigate the efficacy of deep convolutional neural networks (CNNs) in simulating BEC ground states.
  • To develop a computationally efficient method for predicting BEC ground-state wave functions.
  • To assess the precision and generalizability of CNN-based simulations.

Main Methods:

  • Training a deep convolutional neural network using parameters from the dimensionless Gross-Pitaevskii equation (GPE).

Related Experiment Videos

  • Inputting GPE parameters and outputting the corresponding ground-state wave function.
  • Benchmarking the trained neural network with varying coupling strengths and arbitrary potentials.

    • Main Results:

    • The neural network accurately generates ground-state wave functions for both single-component and two-component BECs.
    • High precision was achieved, with relative chemical potential error magnitudes below 10^-3.
    • The neural network demonstrated predictive capabilities for potentials it was not explicitly trained on.

    Conclusions:

    • Deep convolutional neural networks offer a powerful and precise tool for simulating Bose-Einstein condensate ground states.
    • This machine learning approach can efficiently represent continuous wave functions, overcoming limitations of traditional numerical methods.
    • The trained neural network shows promise for predicting BEC properties under diverse conditions.