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 fuzzy neural network for knowledge learning

H C Fu1, J J Shann

  • 1Department of Computer Science and Information Engineering, National Chiao-Tung University, Hsinchu, Taiwan, R.O.C.

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

[Predicting response to non-small cell lung cancer immunotherapy using pre-treatment contrast-enhanced CT texture-based classification].

Zhonghua zhong liu za zhi [Chinese journal of oncology]·2021
Same author

Geometric decoherence of valley excitons in monolayer transition metal dichachogenides.

Journal of physics. Condensed matter : an Institute of Physics journal·2017
Same author

Chiral topological excitons in the monolayer transition metal dichalcogenides.

Scientific reports·2017
Same author

Androgen receptor inclusions acquire GRP78/BiP to ameliorate androgen-induced protein misfolding stress in embryonic stem cells.

Cell death & disease·2013
Same author

User adaptive handwriting recognition by self-growing probabilistic decision-based neural networks.

IEEE transactions on neural networks·2008
Same author

Divide-and-conquer learning and modular perceptron networks.

IEEE transactions on neural networks·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 capable of efficiently learning fuzzy logic rules. The proposed backpropagation-like algorithm rapidly tunes network parameters, achieving precise knowledge acquisition with minimal error.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Fuzzy Logic Systems

Background:

  • Fuzzy logic rule-based systems require effective methods for knowledge acquisition and refinement.
  • Traditional neural network training can be time-consuming and may not optimally capture fuzzy system knowledge.

Purpose of the Study:

  • To develop a fuzzy neural network (FNN) that can learn the knowledge embedded in fuzzy logic rule-based systems.
  • To propose an efficient learning algorithm for training the FNN and fine-tuning its parameters.

Main Methods:

  • A five-layer fuzzy neural network architecture is presented, including Input, Membership-function, AND, OR, and Defuzzification layers.
  • A backpropagation-like learning algorithm is developed to train the network, focusing on parameter adjustments for AND (minimum) and OR (maximum) operations.

Related Experiment Videos

  • The algorithm utilizes gradient descent search for precise knowledge acquisition.

    • Main Results:

    • The proposed learning algorithm demonstrates faster convergence compared to conventional backpropagation methods.
    • The network successfully acquires precise knowledge by focusing weight adjustments on dominant terms.
    • In simulations of the truck backer-upper problem, the network achieved training in dozens of epochs with an error rate below 1%.

    Conclusions:

    • The developed fuzzy neural network and its learning algorithm offer a rapid and effective approach to acquiring knowledge from fuzzy logic systems.
    • The method enables precise parameter tuning, leading to high accuracy in complex control tasks.
    • This approach significantly improves the efficiency of learning fuzzy rules and system parameters.