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

Approximation techniques for neuromimetic calculus.

V Vigneron1, C Barret

  • 1CEMIF, Université d'Evry, France.

International Journal of Neural Systems
|November 24, 1999
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

The design and evaluation of electromyography and inertial biofeedback in hand motor therapy gaming.

Assistive technology : the official journal of RESNA·2020
Same author

Predictive simulation of surgery effect on cerebral palsy gait.

Computer methods in biomechanics and biomedical engineering·2017
Same author

Functional Biomedical Images of Alzheimer's Disease. A Green's Function-based Empirical Mode Decomposition Study.

Current Alzheimer research·2016
Same author

Alzheimer's Disease Brain Areas: The Machine Learning Support for Blind Localization.

Current Alzheimer research·2016
Same author

Predicting postoperative knee flexion during gait of cerebral palsy children.

Computer methods in biomechanics and biomedical engineering·2015
Same author

Leachate pre-treatment strategies before recirculation in landfill bioreactors.

Water science and technology : a journal of the International Association on Water Pollution Research·2005
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

Approximation Theory is crucial for modern statistical methods, especially Neural Network modeling. This survey covers known results for neurone-like networks and their links to statistical concepts like ordinary least squares.

Area of Science:

  • Mathematics
  • Computer Science
  • Statistics

Background:

  • Approximation Theory is fundamental to statistical methods.
  • Neural networks are powerful tools for approximating complex data structures.
  • Understanding neurone-like network capabilities is essential for statistical modeling.

Purpose of the Study:

  • To survey known results in Approximation Theory for neurone-like networks.
  • To highlight the connections between neural networks and classical statistical techniques.
  • To provide a comprehensive overview of approximation capabilities in neural network models.

Main Methods:

  • Literature review of Approximation Theory results.
  • Analysis of neurone-like network architectures and their approximation properties.

Related Experiment Videos

  • Comparative study with classical statistical methods like ordinary least squares.

    • Main Results:

    • Neural networks can approximate metric data structures extensively, either wholly or piecewise.
    • A significant body of research exists on the approximation capabilities of neurone-like units.
    • Strong parallels are drawn between neural network approximation and traditional statistical approaches.

    Conclusions:

    • Approximation Theory is a key enabler for advanced statistical modeling using neural networks.
    • The study reinforces the theoretical underpinnings of neural networks in approximating data.
    • Connections to ordinary least squares (LS) provide a bridge between modern and classical statistics.