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

Natural learning in NLDA networks.

Ana González1, José R Dorronsoro

  • 1Depto. de Ingeniería Informática and Instituto de Ingeniería del Conocimiento, Universidad Autónoma de Madrid, 28049 Madrid, Spain.

Neural Networks : the Official Journal of the International Neural Network Society
|May 8, 2007
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

Changes in serological, inflammatory, and serum protein electrophoretic markers during ongoing meglumine antimoniate plus allopurinol therapy in canine leishmaniosis.

Veterinary research communications·2026
Same author

Detection of circulating immune complexes in feline leishmaniosis: first evidence and diagnostic implications.

Veterinary research communications·2026
Same author

Evaluation of a commercial multispecies rapid test for anti-Leishmania infantum antibodies in unconventional animal species.

Veterinary research communications·2026
Same author

Habits in Pavlovian learning: Resistance to devaluation by sensory-specific satiety following extensive exposure to palatable tastes.

Psychonomic bulletin & review·2026
Same author

"Appropriate and Fair": Modeling Equitable Compensation for Lived Experience Experts in Local Public Health Programming.

Progress in community health partnerships : research, education, and action·2026
Same author

Electrochromic polyoxometalates for sensing abiotic stress in plants.

Frontiers in plant science·2026
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

This study introduces natural-like gradients for Non-Linear Discriminant Analysis (NLDA) networks, significantly improving training convergence speed compared to standard gradient descent. The novel approach enhances the efficiency of NLDA network optimization.

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Pattern Recognition

Background:

  • Non-Linear Discriminant Analysis (NLDA) networks integrate Multilayer Perceptrons (MLP) with Fisher's criterion minimization.
  • Efficient training of NLDA networks is crucial for advancing pattern recognition tasks.

Purpose of the Study:

  • To define and implement natural-like gradients for NLDA network training.
  • To enhance the convergence speed and efficiency of NLDA network optimization.

Main Methods:

  • A simplified procedure for defining natural-like gradients based on the expectation of the NLDA criterion's gradient.
  • Calculation of the Fisher information matrix using the defined gradient.
  • Analytical and numerical comparisons with standard gradient descent and MLP training.

Related Experiment Videos

Main Results:

  • The proposed natural-like gradient approach demonstrates significantly faster convergence than standard gradient descent for NLDA networks.
  • The Hessian and information matrices for NLDA training differ from those in standard MLP or square error functions.
  • The faster convergence is not attributable to the Gauss-Newton method, unlike in natural MLP batch training.

Conclusions:

  • The novel natural-like gradient method offers a computationally efficient and faster alternative for training NLDA networks.
  • This approach provides a valuable tool for optimizing complex pattern recognition models.
  • Further research can explore the theoretical underpinnings and broader applications of these gradients.