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

Learning fuzzy decision trees.

Bruno Apolloni1, Giacomo Zamponi, Anna Maria Zanaboni

  • 1Dipartimento di Scienze dell'lnformazione, Università di Milano, 20135, Milano, Italy

Neural Networks : the Official Journal of the International Neural Network Society
|March 29, 2003
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

Exploring the Association of Migraine Susceptibility SNPs With the Risk of Chronic Migraine.

European journal of pain (London, England)·2025
Same author

Framing the meat consumption transition: A statistical learning approach to explore the factors shaping young adults' food choices in Germany and Italy.

Meat science·2025
Same author

Insights into the Involvement of TRPA1 Channels in the Neuro-Inflammatory Machinery of Trigeminal Neuralgia.

Molecules (Basel, Switzerland)·2025
Same author

Fatal fall from a height: is it possible to apply artificial intelligence techniques for height estimation?

International journal of legal medicine·2024
Same author

Intranasal administration of recombinant human BDNF as a potential therapy for some primary headaches.

The journal of headache and pain·2024
Same author

Lack of association between TRPV1 gene polymorphisms and risk of migraine chronification: a case-control study and meta-analysis.

Neurological sciences : official journal of the Italian Neurological Society and of the Italian Society of Clinical Neurophysiology·2024
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

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

New results on prescribed-time synchronization of complex networks via intermittent control.

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

Variance-constrained multi-view ensemble broad network for imbalanced data.

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

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

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

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

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

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

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

A recurrent neural network learns to guide decision tree traversals by assigning fuzzy membership values to potential moves. This approach enables continuous parameter learning for discrete decision processes, optimizing solutions and move sequences.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Linguistics

Background:

  • Decision trees are fundamental structures for sequential decision-making.
  • Guiding discrete state processes with continuous methods presents a significant challenge.
  • Natural language processing tasks, like sentence disambiguation, require complex decision pathways.

Purpose of the Study:

  • To develop a recurrent neural network capable of suggesting optimal moves within a decision tree structure.
  • To integrate fuzzy logic for representing the 'goodness' of moves, enabling probabilistic selection.
  • To enable incremental learning on continuous neural network parameters to drive discrete decision processes.

Main Methods:

  • A recurrent neural network architecture was employed to learn move suggestions.

Related Experiment Videos

  • Fuzzy membership values were used to quantify the suitability of child nodes (moves).
  • The learning process focused on linking local move decisions to the global suitability of the final solution.

    • Main Results:

    • The neural network successfully learned to suggest moves, guiding descent along decision tree branches.
    • Fuzzy values effectively translated into probabilities for selecting the next move.
    • The model demonstrated the ability to optimize both solution quality and the sequence of decisions leading to it.

    Conclusions:

    • Recurrent neural networks can effectively learn to navigate decision trees using fuzzy logic.
    • This method provides a robust way to bridge continuous neural network learning with discrete decision-making.
    • The approach shows promise for complex tasks such as natural language sentence disambiguation.