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

Constructive neural networks with piecewise interpolation capabilities for function approximations.

C H Choi1, J Y Choi

  • 1Dept. of Control and Instrum. Eng., Seoul Nat. Univ.

IEEE Transactions on Neural Networks
|January 1, 1994
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

First Measurement of Missing Energy due to Nuclear Effects in Monoenergetic Neutrino Charged-Current Interactions.

Physical review letters·2025
Same author

A kalihinol analog disrupts apicoplast function and vesicular trafficking in <i>P. falciparum</i> malaria.

Science (New York, N.Y.)·2024
Same author

A Potent Kalihinol Analogue Disrupts Apicoplast Function and Vesicular Trafficking in <i>P. falciparum</i> Malaria.

bioRxiv : the preprint server for biology·2023
Same author

Association of body mass index and bloodstream infections in patients on extracorporeal membrane oxygenation: a single-centre, retrospective, cohort study.

The Journal of hospital infection·2023
Same author

Impact of tuberculosis on the incidence of osteoporosis and osteoporotic fractures: a nationwide population-based cohort study.

Public health·2023
Same author

Potential overestimation of cognitive impairment because of hearing loss: impact of test modalities on cognitive test scores.

The Journal of laryngology and otology·2023
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

This study introduces a novel constructive neural network using space tessellation for function approximation. This approach enhances training efficiency and data generalization capabilities.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Approximating continuous functions is a fundamental challenge in machine learning.
  • Standard neural networks can face difficulties with training time and local minima.
  • Improving generalization for new data is crucial for practical applications.

Purpose of the Study:

  • To propose a constructive neural network with local interpolation capabilities.
  • To leverage space tessellation for function approximation.
  • To enhance training efficiency and generalization performance.

Main Methods:

  • Devised a neural network using space tessellation with nonoverlapping hyperpolyhedral convex cells.
  • Introduced neural network granules (NNGs) processed in parallel for local mapping.

Related Experiment Videos

  • Calculated plastic weights within NNGs for training data implementation.

    • Main Results:

    • The proposed network demonstrates piecewise linear or nonlinear local interpolation.
    • Reduced training time and alleviated local minima issues.
    • Improved generalization for new data within convex cells.

    Conclusions:

    • The constructive neural network effectively approximates continuous functions.
    • The tessellation-based approach offers advantages in training and generalization.
    • While increasing network size, parallel architecture maintains retrieval response speed.