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

Training Feedforward Neural Networks: An Algorithm Giving Improved Generalization.

Charles W. Lee1

  • 1Bolton Institute, UK

Neural Networks : the Official Journal of the International Neural Network Society
|January 1, 1997
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 journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

New results on prescribed-time synchronization of complex networks via intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Variance-constrained multi-view ensemble broad network for imbalanced data.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

A new algorithm for supervised training in multilayer feedforward neural networks offers faster convergence and improved generalization. This method preserves the error backpropagation system, enhancing neural network performance.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Supervised training is crucial for developing effective multilayer feedforward neural networks.
  • The gradient descent backpropagation algorithm is a standard but can be slow and prone to generalization issues.

Purpose of the Study:

  • To derive a novel algorithm for supervised training of multilayer feedforward neural networks.
  • To evaluate the performance of the new algorithm against the traditional gradient descent backpropagation method.

Main Methods:

  • Development of a new supervised training algorithm for feedforward neural networks.
  • Comparative analysis of the new algorithm with gradient descent backpropagation, focusing on convergence speed and generalization capabilities.
  • Ensuring the preservation of the error backpropagation mechanism within the new algorithm.

Related Experiment Videos

Main Results:

  • The derived algorithm demonstrates faster convergence compared to gradient descent backpropagation.
  • The algorithm also shows improved generalization performance.
  • The core system of backpropagating errors through the network is maintained.

Conclusions:

  • The novel algorithm presents a significant improvement over existing methods for supervised neural network training.
  • It offers a more efficient and effective approach to developing high-performing neural networks.