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

Measuring the VC-dimension using optimized experimental design.

X Shao1, V Cherkassky, W Li

  • 1ECE Department, University of Minnesota, Minneapolis, MN 55455, USA.

Neural Computation
|August 23, 2000
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

Model complexity control for regression using VC generalization bounds.

IEEE transactions on neural networks·2008
Same author

Self-organizing maps for the skeletonization of sparse shapes.

IEEE transactions on neural networks·2008
Same author

Computational intelligence in earth sciences and environmental applications: issues and challenges.

Neural networks : the official journal of the International Neural Network Society·2006
Same author

Myopotential denoising of ECG signals using wavelet thresholding methods.

Neural networks : the official journal of the International Neural Network Society·2001
Same author

Signal estimation and denoising using VC-theory.

Neural networks : the official journal of the International Neural Network Society·2001
Same author

Footprinting of yeast DNA topoisomerase II lysyl side chains involved in substrate binding and interdomainal interactions.

The Journal of biological chemistry·1998
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

Estimating model complexity using VC-dimension can be inaccurate. This study proposes an improved experimental design for more accurate VC-dimension estimation, enhancing complexity control and prediction accuracy.

Area of Science:

  • Machine Learning
  • Statistical Learning Theory

Background:

  • VC-dimension measures model complexity in VC-theory, crucial for generalization bounds.
  • Analytic estimation of VC-dimension is often infeasible.
  • Experimental estimation exists but can suffer from sample variability.

Purpose of the Study:

  • To improve the accuracy of experimental VC-dimension estimation.
  • To propose an optimized experimental design procedure.
  • To enhance complexity control and prediction accuracy.

Main Methods:

  • Proposed a nonuniform design structure for measurement points (sample size, repetitions).
  • Compared the proposed design with the uniform design of Vapnik et al. (1994).
  • Evaluated accuracy of VC-dimension estimation and its impact on generalization bounds.

Related Experiment Videos

Main Results:

  • The proposed optimized design structure yields more accurate VC-dimension estimates.
  • Improved VC-dimension estimation leads to better complexity control.
  • Enhanced complexity control results in improved prediction accuracy.

Conclusions:

  • The optimized experimental design significantly improves VC-dimension estimation accuracy.
  • Accurate VC-dimension estimation is vital for effective complexity control.
  • This method enhances prediction accuracy in machine learning models.