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

Towards more practical average bounds on supervised learning.

H Gu1, H Takahashi

  • 1Dept. of Commun. and Syst. Eng., Univ. of Electro-Commun., Chofu.

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

Baseline Gut Microbiome-Metabolome Signatures Are Associated with Drinking Severity and Reduction Following Dutasteride Treatment in Alcohol Use Disorder.

medRxiv : the preprint server for health sciences·2026
Same author

Longitudinal assessment of food insecurity status on the gut microbiome and metabolome of first-year college students.

The British journal of nutrition·2025
Same author

Professional clarity.

British dental journal·2024
Same author

[Compound <i>Yuye</i> Decoction protects diabetic rats against cardiomyopathy by inhibiting myocardial apoptosis and inflammation <i>via</i> regulating the PI3K/Akt signaling pathway].

Nan fang yi ke da xue xue bao = Journal of Southern Medical University·2024
Same author

Adherence to the EAT-Lancet diet reduces the risk of head and neck cancers in 101,755 American adults: a prospective cohort study.

Public health·2024
Same author

China's prevention and control experience of echinococcosis: A 19-year retrospective.

Journal of helminthology·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

This study introduces a novel method for analyzing learning generalization performance using hypothesis testing inequalities. It offers a unified view of learning curves, overcoming limitations of existing theories and providing insights into system generalization.

Area of Science:

  • Machine Learning
  • Statistical Learning Theory

Background:

  • Existing theories like Vapnik-Chervonenkis (VC) theory often present pessimistic generalization bounds.
  • Analyzing average-case learning performance in realistic scenarios, especially outside the Bayesian framework, remains a challenge.

Purpose of the Study:

  • To develop a unified theory for studying average generalization performance in machine learning.
  • To provide a more optimistic and insightful perspective on generalization compared to existing methods.
  • To establish bounds on learning curves directly linked to system complexity (adjustable weights).

Main Methods:

  • Utilizing hypothesis testing inequalities to directly study average generalization performance.
  • Developing a theoretical framework applicable to concept learning and regression.

Related Experiment Videos

  • Employing numerical simulations to validate the proposed theory.

    • Main Results:

    • The theory offers a unified viewpoint for average-case learning curves.
    • It alleviates the practical pessimism associated with VC theory and similar approaches.
    • Generalization bounds are shown to be directly related to the number of adjustable system weights.

    Conclusions:

    • The proposed method provides a valuable tool for understanding and analyzing generalization in machine learning.
    • The theory offers broader insights into generalization and system complexity.
    • It demonstrates applicability to complex models like combinations of neural networks.