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 adaptive learning control network with on-line structure and parameter learning

C J Lin1

  • 1Department of Electronic Engineering, Nan-Kai Junior College of Technology & Commerce, Tsaotun, Taiwan, R.O.C.

International Journal of Neural Systems
|November 1, 1996
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

Impact of Mandatory Clinical Ethics Consultation for Neurocritically Ill Patients.

Journal of bioethical inquiry·2026
Same author

Breakup dynamics of weakly bound nuclei at energies around the Coulomb barrier.

Fundamental research·2025
Same author

Measurement of Electron Antineutrino Oscillation Amplitude and Frequency via Neutron Capture on Hydrogen at Daya Bay.

Physical review letters·2024
Same author

[Analysis of factors for anxiety and anxiety tendency in tinnitus patients].

Zhonghua yi xue za zhi·2024
Same author

Search for a Sub-eV Sterile Neutrino Using Daya Bay's Full Dataset.

Physical review letters·2024
Same author

The applicability of the "surprise question" as a prognostic tool in patients with severe chronic comorbidities in a university teaching outpatient setting.

BMC medical education·2023
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 the Fuzzy Adaptive Learning Control Network (FALCON) and Reinforcement FALCON (RFALCON) for dynamic fuzzy logic control systems. These models autonomously learn control strategies from data, avoiding combinatorial complexity and enabling real-time adaptation.

Area of Science:

  • Artificial Intelligence
  • Control Systems Engineering
  • Machine Learning

Background:

  • Traditional fuzzy logic control systems often suffer from combinatorial complexity in partitioning input/output spaces as variables increase.
  • Existing methods may require significant a priori knowledge or initial setup for fuzzy logic control systems.
  • Obtaining exact training data for real-time applications can be challenging and costly.

Purpose of the Study:

  • To introduce a novel connectionist model, the Fuzzy Adaptive Learning Control Network (FALCON), for realizing fuzzy logic control.
  • To develop an on-line supervised learning algorithm for dynamic construction of FALCON, combining backpropagation and fuzzy ART.
  • To propose a Reinforcement FALCON (RFALCON) for scenarios where exact training data is unavailable, utilizing reward/penalty signals.

Related Experiment Videos

Main Methods:

  • Dynamic construction of FALCON using an on-line supervised structure/parameter learning algorithm.
  • Flexible partitioning of input/output spaces using irregular fuzzy hyperboxes based on training data distribution.
  • Integration of two FALCONs (critic and action networks) with temporal difference techniques and stochastic exploration for RFALCON.

Main Results:

  • FALCON dynamically constructs fuzzy logic control systems without requiring a priori knowledge.
  • The proposed learning algorithm partitions state and control spaces flexibly, avoiding combinatorial growth.
  • RFALCON successfully constructs a control system using only reward/penalty signals, demonstrated on a ball and beam balancing system.

Conclusions:

  • FALCON and RFALCON offer autonomous and adaptive solutions for fuzzy logic control.
  • The flexible partitioning strategy effectively addresses the complexity of multi-variable systems.
  • The proposed reinforcement learning approach enables control system development in data-scarce environments.