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

Advanced neural-network training algorithm with reduced complexity based on Jacobian deficiency.

G Zhou1, J Si

  • 1Department of Electrical Engineering, Arizona State University, Tempe, AZ 85287-5706, USA.

IEEE Transactions on Neural Networks
|February 7, 2008
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

[Clinical features and fistula acoustic characteristics in maintenance hemodialysis patients with versus without diabetes mellitus].

Zhonghua yi xue za zhi·2026
Same author

X-linked hypophosphatemic rickets: a rare case report.

Acta orthopaedica Belgica·2026
Same author

[Kidney transplantation in low-age, low-weight children: A report of two cases].

Beijing da xue xue bao. Yi xue ban = Journal of Peking University. Health sciences·2025
Same author

[The clinical research of IFNGR1 proximal promoter polymorphism in susceptibility and prognosis of breast cancer].

Zhonghua yu fang yi xue za zhi [Chinese journal of preventive medicine]·2025
Same author

The lipidomic profiling of ovine sperm reveals metabolic alterations and key biomarkers after cryopreservation.

Cryo letters·2025
Same author

Normal tissue complication probability model predicting taste impairment in head and neck cancer patients: Evaluating the taste bud bearing tongue mucosa as a predictor.

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology·2025
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

A new supervised training method for neural networks, based on Jacobian rank deficiency, significantly improves convergence and reduces complexity compared to existing algorithms like Levenberg-Marquardt.

Area of Science:

  • Machine Learning
  • Neural Networks
  • Optimization

Background:

  • Supervised training of neural networks is crucial for various applications.
  • Existing methods like backpropagation and Levenberg-Marquardt have limitations in convergence, accuracy, and computational efficiency.
  • Levenberg-Marquardt algorithm, while effective for nonlinear least squares, presents higher computational and memory demands.

Purpose of the Study:

  • To introduce an advanced supervised training method for neural networks.
  • To improve convergence properties of neural network training.
  • To reduce memory and computation complexities in supervised training.

Main Methods:

  • Developed a novel supervised training method based on Jacobian rank deficiency.

Related Experiment Videos

  • Formulated the method in the spirit of the Gauss-Newton algorithm.
  • Utilized extensive simulation results for validation.

    • Main Results:

    • The new method demonstrates superior performance compared to the Levenberg-Marquardt algorithm.
    • Achieved significant improvements in convergence properties.
    • Reduced computational and memory complexities during training.

    Conclusions:

    • The proposed Jacobian rank deficiency-based method offers a more efficient and effective approach to supervised neural network training.
    • This advanced method outperforms the Levenberg-Marquardt algorithm in key training metrics.
    • The findings suggest a promising new direction for optimizing neural network training processes.