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 neuro-fuzzy framework for inferencing.

Sukumar Chakraborty1, Kuhu Pal, Nikhil R Pal

  • 1Interra Information Technologies (India) Pvt. Ltd, Salt Lake City, Calcutta.

Neural Networks : the Official Journal of the International Neural Network Society
|May 23, 2002
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

Efficient High-Dimensional Learning With Adaptive Gaussian RBF Networks.

IEEE transactions on neural networks and learning systems·2025
Same author

Leader-Following Consensus of Time-Scale-Type Heterogeneous Nonlinear MASs via Periodic Event-Triggered Control.

IEEE transactions on cybernetics·2025
Same author

Event-Triggered Finite-Time Stabilization of Delayed T-S Fuzzy Systems on Time Scales.

IEEE transactions on cybernetics·2025
Same author

Boosting Drug-Disease Association Prediction for Drug Repositioning via Dual-Feature Extraction and Cross-Dual-Domain Decoding.

Journal of chemical information and modeling·2025
Same author

Unsupervised Feature Selection for High-Order Embedding Learning and Sparse Learning.

IEEE transactions on cybernetics·2025
Same author

Bi-Level Spectral Feature Selection.

IEEE transactions on neural networks and learning systems·2024
Same journal

A practical design of backdoor trigger under frequency-based orthogonality constraints.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

EEG fine-grained visual semantic decoding via a multimodal framework.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Collaborative-adversarial jailbreaking: A propagation-aware attack framework for multi-agent code generation systems.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Theoretical analysis of the denoising autoencoder using Tweedie's formula.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Frequency-based cross-attention fusion network for RGB-D salient object detection.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

HTNet: A self-supervised heterogeneous triple network for multi-modal data.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces COIN, a neural network for compositional rule of inference (COI) that handles complex rules. COIN learns fuzzy rule representations, outperforming traditional methods for improved inferencing outcomes.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Fuzzy Logic Systems

Background:

  • Compositional Rule of Inference (COI) is crucial for logical reasoning in AI.
  • Previous connectionist models were limited to single-clause antecedents.
  • Handling multi-clause antecedents in fuzzy rule-based systems remains a challenge.

Purpose of the Study:

  • To generalize a connectionist COI model to accommodate rules with multiple antecedent clauses.
  • To introduce COIN (Compositional Inferencing Network) for relational rule representation.
  • To enable neural learning of fuzzy rule representations, avoiding manual selection of implication functions.

Main Methods:

  • Generalization of a prior connectionist COI network to handle multi-clause antecedents.

Related Experiment Videos

  • Development of the COIN architecture for relational rule representation.
  • Neural learning of fuzzy rule relations with connection weights constrained to [0,1].

    • Main Results:

    • COIN successfully implements COI for rules with multi-clause antecedents.
    • Neural learning automatically identifies effective fuzzy rule representations.
    • The learned representations yield significantly better conclusions compared to standard implication methods.

    Conclusions:

    • COIN provides an effective neural network approach for compositional rule of inference with complex fuzzy rules.
    • Automatic learning of fuzzy rule representations by COIN surpasses traditional implication functions.
    • The proposed method enhances the accuracy and performance of fuzzy inferencing systems.