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

Rule extraction with fuzzy neural network

F D'Alché-Buc1, V Andrès, J P Nadal

  • 1Laboratoires d'Electronique Philips, Limeil-Brévannes, France.

International Journal of Neural Systems
|March 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

How do pig farms maintain low Salmonella prevalence: a case-control study.

Epidemiology and infection·2018
Same author

Maternal vaccination as a Salmonella Typhimurium reduction strategy on pig farms.

Journal of applied microbiology·2017
Same author

Study of the impact on Salmonella of moving outdoor pigs to fresh land.

Epidemiology and infection·2017
Same author

[Hospital readmission after postpartum discharge of term newborns in two maternity wards in Stockholm and Marseille].

Archives de pediatrie : organe officiel de la Societe francaise de pediatrie·2016
Same author

Loss of p27 phosphorylation at Ser10 accelerates early atherogenesis by promoting leukocyte recruitment via RhoA/ROCK.

Journal of molecular and cellular cardiology·2015
Same author

[Biochemical characterization of the optic nerve in mice overexpressing the P53 gen. Oxidative stress assays].

Archivos de la Sociedad Espanola de Oftalmologia·2008
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

This study introduces a novel fuzzy neural network for extracting understandable decision rules. The system uses a unique fuzzy neuron and a sequential learning procedure, successfully applied to inverted pendulum control.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Fuzzy Systems

Background:

  • Connectionist systems often lack interpretable decision rules.
  • Existing methods for fuzzy rule extraction can be complex.
  • Need for systems that combine learning capabilities with rule understandability.

Purpose of the Study:

  • To develop a fuzzy neural network capable of learning understandable decision rules.
  • To implement a novel fuzzy neuron for approximating fuzzy operations.
  • To create a sequential learning procedure for efficient network training.

Main Methods:

  • Utilized a fuzzy neural network with a novel fuzzy neuron computing max-min operations.
  • Employed a sequential learning procedure with backpropagation and a custom cost function.

Related Experiment Videos

  • Developed a method for automatic reduction of rule condition-parts during learning.

    • Main Results:

    • The fuzzy neural network successfully extracted understandable fuzzy control rules.
    • The novel fuzzy neuron enabled possibilistic inference within the network.
    • The learning procedure allowed sequential training and automatic rule simplification.
    • Demonstrated effectiveness on an inverted pendulum control task.

    Conclusions:

    • The proposed fuzzy neural network provides a viable approach for learning interpretable fuzzy control rules.
    • The max-min fuzzy neuron offers a unique interpretation as a possibility estimator.
    • The sequential learning method enhances the practicality of training complex fuzzy systems.