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 by successive regularization.

M Ishikawa1

  • 1Department of Brain Science and Engineering, Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, Fukuoka, Japan. ishikawa@ces.kyutech.ac.jp

Neural Networks : the Official Journal of the International Neural Network Society
|January 13, 2001
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

Yolk vitronectin. Purification and differences from its blood homologue in molecular size, heparin binding, collagen binding, and bound carbohydrate.

The Journal of biological chemistry·1992
Same author

Scanning electron microscopy of intracellular organelles in the young odontoblasts of rats.

Scanning microscopy·1992
Same author

Effects of social isolation on pentobarbital activity in mice: relationship to racemate levels and enantiomer levels in brain.

The Journal of pharmacology and experimental therapeutics·1992
Same author

Protection by chlorpromazine against lethality and renal toxicity of cisplatin in mice.

Experientia·1992
Same author

Granulocyte-colony stimulating factor stimulates immunoreactive endothelin-1 release from cultured bovine endothelial cells.

European journal of pharmacology·1992
Same author

[Epidemiological study of infantile intractable hydrocephalus in Japan].

Nihon rinsho. Japanese journal of clinical medicine·1992
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

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

Decentralized ADMM for factorization-based Low-rank matrix estimation.

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

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

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

This study introduces successive regularization, a novel method for rule extraction in artificial intelligence. This approach enhances knowledge acquisition by generating dominant rules first, leading to superior data explanation.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Biology

Background:

  • Knowledge acquisition is crucial for advancing artificial intelligence.
  • Rule extraction from neural networks offers computational simplicity and generalization capabilities.
  • Existing methods may lack robustness or intuitive understanding.

Purpose of the Study:

  • To propose a novel rule extraction technique called successive regularization.
  • To improve the efficiency and interpretability of knowledge acquisition from neural networks.
  • To demonstrate the method's effectiveness across diverse datasets.

Main Methods:

  • Successive regularization generates dominant rules early and exceptions later.
  • The method emphasizes computational robustness and enhanced understanding.

Related Experiment Videos

  • Applied to mushroom classification, DNA promoter recognition, and iris classification.

    • Main Results:

    • Empirical results show superior performance in rule extraction.
    • The method yields a reduced number and size of explanatory rules.
    • Demonstrates effectiveness in diverse classification and recognition tasks.

    Conclusions:

    • Successive regularization is an effective approach for knowledge acquisition.
    • The method offers advantages in computational robustness and interpretability.
    • It provides a promising direction for advancing artificial intelligence.