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

Fast Second Order Learning Algorithm for Feedforward Multilayer Neural Networks and its Applications.

Maciej Stodolski1, Piotr Bojarczak, Stanislaw Osowski

  • 1Warsaw University of Technology, Radom, Poland

Neural Networks : the Official Journal of the International Neural Network Society
|December 1, 1996
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

Application of Deep Learning Networks to Segmentation of Surface of Railway Tracks.

Sensors (Basel, Switzerland)·2021
Same author

Routine preoperative mechanical bowel preparation with additive oral antibiotics is associated with a reduced risk of anastomotic leakage in patients undergoing elective oncologic resection for colorectal cancer.

World journal of surgical oncology·2019
Same author

Advanced gallbladder inflammation is a risk factor for gallbladder perforation in patients with acute cholecystitis.

World journal of emergency surgery : WJES·2018
Same author

Risk of recurrence following mesh associated incisional hernia repair using the retromuscular technique in patients with relevant medical conditions.

Asian journal of surgery·2018
Same author

Computerized System for Quantitative Assessment of Atherosclerotic Plaques in the Femoral and Iliac Arteries Visualized by Multislice Computed Tomography.

IEEE transactions on bio-medical engineering·2015
Same author

Computerized system for recognition of autism on the basis of gene expression microarray data.

Computers in biology and medicine·2014
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 an efficient training program for multilayer feedforward neural networks using advanced optimization algorithms. The method proves effective for complex signal processing tasks, offering a novel, accurate solution.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Multilayer feedforward neural networks require efficient training methods for complex tasks.
  • Existing optimization algorithms may not fully address the challenges of high-dimensional problems.

Purpose of the Study:

  • To present an efficient training program for multilayer feedforward neural networks.
  • To demonstrate the algorithm's effectiveness on standard and high-dimensional problems.
  • To explore neural networks as a nonconventional solution for signal processing tasks.

Main Methods:

  • Utilizing second-order optimization algorithms, including variable metric and conjugate gradient methods.
  • Incorporating directional minimization in each training step.

Related Experiment Videos

  • Testing the algorithm on benchmark datasets (parity, dichotomy, logistic, two-spiral) and real-world applications (deconvolution, source separation, nonlinear dynamic plant identification).

    • Main Results:

    • The training program demonstrated efficiency on standard benchmark problems.
    • Successful application to higher dimensionality problems like deconvolution and source separation was achieved.
    • Neural networks trained with this algorithm provided satisfactory accuracy for signal processing tasks.

    Conclusions:

    • The proposed efficient training program effectively trains multilayer feedforward neural networks.
    • This approach offers a viable and accurate nonconventional solution for various signal processing challenges.
    • The algorithm's performance is validated through numerical experiments on diverse problems.