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 capacity and sample complexity on expert networks.

L Fu1

  • 1Dept. of Comput. and Inf. Sci., Florida Univ., Gainesville, FL.

IEEE Transactions on Neural Networks
|January 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

Management of Medullary Thyroid Carcinoma: Integrating World Health Organization Grading and Molecular Targets for Precision Therapy.

Clinical oncology (Royal College of Radiologists (Great Britain))·2026
Same author

[Non-invasive and high-precision identification of gastric precancerous lesions based on SERS and machine learning].

Zhonghua zhong liu za zhi [Chinese journal of oncology]·2026
Same author

Copper-catalyzed three-component thiocyanosulfonylation of allenes.

Chemical communications (Cambridge, England)·2026
Same author

[Recurrence of peripheral anterior synechiae following phacoemulsification combined with intraocular lens implantation and goniosynechialysis in primary angle-closure glaucoma: an intermediate and long-term analysis].

[Zhonghua yan ke za zhi] Chinese journal of ophthalmology·2026
Same author

[The impact of myocardial infarct size dynamics on left ventricular remodeling in STEMI patients after primary percutaneous coronary intervention].

Zhonghua xin xue guan bing za zhi·2025
Same author

GPER-1 Rapid Regulation Influences p-Akt Expression to Resist Stress-Induced Injuries in a Sex-Specific Manner.

Physiological research·2024
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

Expert networks integrate symbolic rules into neural networks, enhancing generalization. They reduce dimensionality, requiring fewer training samples than traditional multilayered perceptrons for effective learning.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Knowledge-based neural networks integrate symbolic expert knowledge.
  • Expert networks map symbolic expert systems' uncertainty management to neural network activation functions.

Purpose of the Study:

  • To explain why expert networks generalize better than multilayered perceptrons with limited data.
  • To provide a formal analysis of expert network generalization capabilities.

Main Methods:

  • Formal analysis of generalization dimensionality in expert networks.
  • Comparison of expert networks with multilayered perceptrons regarding sample size requirements.

Main Results:

  • Expert networks demonstrate reduced generalization dimensionality.

Related Experiment Videos

  • Expert networks require smaller sample sizes for effective generalization compared to multilayered perceptrons.

    • Conclusions:

    • Expert networks offer superior generalization from finite datasets.
    • The integration of symbolic rules enhances the learning efficiency of neural networks.