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

A function approximation algorithm using sequential composition

R Newman1

  • 1Department of Mathematics, University of Western Australia, Nedlands.

International Journal of Neural Systems
|June 1, 1993
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

A mobile gamma-ray LaBr<sub>3</sub>(Ce) detector unit for in-situ radionuclide analysis at TENORM contamination sites.

Journal of environmental radioactivity·2025
Same author

Antiviral effects of oleandrin.

Journal of the American College of Emergency Physicians open·2021
Same author

A splice site variant in the SUV39H2 gene in Greyhounds with nasal parakeratosis.

Animal genetics·2018
Same author

Is the timed loaded standing test a valid measure of back muscle endurance in people with vertebral osteoporosis?

Osteoporosis international : a journal established as result of cooperation between the European Foundation for Osteoporosis and the National Osteoporosis Foundation of the USA·2018
Same author

RNA binding proteins as regulators of immune cell biology.

Clinical and experimental immunology·2015
Same author

Cognitive behavioural therapy best prevents postpartum depression.

BJOG : an international journal of obstetrics and gynaecology·2014
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

A novel neural network method enhances one-dimensional function approximation, especially for complex problems and noisy data. This adaptive algorithm offers improved stability and performance in specific applications.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Multilayer feedforward neural networks are widely used for function approximation.
  • Existing methods face challenges with complex one-dimensional functions and noisy datasets.

Purpose of the Study:

  • To introduce and evaluate a new method for approximating one-dimensional functions using neural network structures.
  • To examine the convergence properties and performance of the proposed method compared to conventional approaches.

Main Methods:

  • Development of a novel approximation method based on the structural capabilities of multilayer feedforward neural networks.
  • Testing the method's convergence properties through a series of examples.
  • Presentation and evaluation of an adaptive version of the algorithm.

Related Experiment Videos

Main Results:

  • The new method demonstrates superior performance over conventional networks for complicated one-dimensional function approximation tasks.
  • The adaptive version shows significant stability and effectiveness in the presence of noisy data.
  • For simple function approximation without noise, conventional methods may perform better.

Conclusions:

  • The developed neural network method offers a valuable tool for complex and noisy one-dimensional function approximation.
  • Adaptability and noise stability are key advantages of this new approach.
  • The method's utility is context-dependent, excelling in specific challenging scenarios.