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 Video

Updated: Jun 23, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

Recurrent neural networks training with stable bounding ellipsoid algorithm.

Wen Yu1, José de Jesús Rubio

  • 1Departamento de Control Automático, CINVESTAV-IPN, México D.F. 07360, México. yuw@ctrl.cinvestav.mx

IEEE Transactions on Neural Networks
|May 19, 2009
PubMed
Summary
This summary is machine-generated.

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

Effects of Liposomal Bupivacaine for Superficial Parasternial Intercostal Plane Block on Postoperative Stress and Analgesia in Patients Undergoing Median Sternotomy: A Prospective, Randomized, Double-Blind Trial.

Drug design, development and therapy·2026
Same author

Panchromatic Polymer Dot-Bacteria Biohybrid Systems for Photosynthetic CO<sub>2</sub> Reduction into Acetic Acid.

ACS nano·2026
Same author

Electrochemical Oxidation of Water Through Conducting Polymer for Hydroxyl Radical Generation at Ultra-Low Voltage.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Association of maternal hemoglobin levels and chorioamnionitis with preterm birth and low birth weight: a cohort study.

World journal of pediatrics : WJP·2026
Same author

Multiomic characterization of response and resistance to neoadjuvant chemoradiotherapy in esophageal squamous cell carcinoma.

Translational cancer research·2026
Same author

Exploring phylosymbiosis in the skin microbiome of coral reef fish: synergistic effects of environmental and host-specific factors.

ISME communications·2026
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

Bounding ellipsoid (BE) algorithms provide efficient and fast training for neural networks. This study introduces an ellipsoid propagation algorithm for training recurrent neural networks in nonlinear systems identification, proving its stability.

Area of Science:

  • Computational intelligence
  • Machine learning
  • Neural network algorithms

Background:

  • Traditional neural network training methods like backpropagation can be computationally intensive.
  • Least squares methods are also used but may have limitations in certain applications.
  • Recurrent neural networks (RNNs) are powerful for modeling dynamic systems.

Purpose of the Study:

  • To propose a novel ellipsoid propagation (BE) algorithm for training recurrent neural networks.
  • To apply the BE algorithm for nonlinear systems identification.
  • To demonstrate the computational efficiency and fast convergence of the proposed algorithm.

Main Methods:

  • Development of the ellipsoid propagation algorithm for weight updates in RNNs.
  • Application to nonlinear systems identification tasks.

More Related Videos

An Automated Squint Method for Time-syncing Behavior and Brain Dynamics in Mouse Pain Studies
05:49

An Automated Squint Method for Time-syncing Behavior and Brain Dynamics in Mouse Pain Studies

Published on: November 1, 2024

Related Experiment Videos

Last Updated: Jun 23, 2026

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
03:31

End-To-End Deep Neural Network for Salient Object Detection in Complex Environments

Published on: December 15, 2023

An Automated Squint Method for Time-syncing Behavior and Brain Dynamics in Mouse Pain Studies
05:49

An Automated Squint Method for Time-syncing Behavior and Brain Dynamics in Mouse Pain Studies

Published on: November 1, 2024

  • Theoretical proof of the algorithm's stability.

    • Main Results:

    • The ellipsoid propagation algorithm trains both hidden and output layers of RNNs.
    • The algorithm demonstrates high computational efficiency.
    • Fast convergence speed was observed during training.

    Conclusions:

    • The proposed ellipsoid propagation algorithm is a viable and efficient alternative for training RNNs.
    • The algorithm is suitable for nonlinear systems identification.
    • The proven stability ensures reliable performance.