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

Generalization Analysis of Fredholm Kernel Regularized Classifiers.

Tieliang Gong1, Zongben Xu2, Hong Chen3

  • 1School of Mathematics and Statistics, Xi'an Jiaotong University, Xi'an 710049, China adidasgtl@gmail.com.

Neural Computation
|April 15, 2017
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

Embryonic arrest at midgestation and disruption of Notch signaling produced by the absence of both epsin 1 and epsin 2 in mice.

Proceedings of the National Academy of Sciences of the United States of America·2009
Same author

Two novel SNPs in coding region of the caprine Fat-inducing transcript gene and their association with growth traits.

Molecular biology reports·2009
Same author

Reprogramming human fibroblasts using HIV-1 TAT recombinant proteins OCT4, SOX2, KLF4 and c-MYC.

Molecular biology reports·2009
Same author

Bioinformatics and microarray analysis of microRNA expression profiles of murine embryonic stem cells, neural stem cells induced from ESCs and isolated from E8.5 mouse neural tube.

Neurological research·2009
Same author

Attenuation of lipopolysaccharide-mediated left ventricular dysfunction by glutamine preconditioning.

The Journal of surgical research·2009
Same author

Differential regulation of Apak by various DNA damage signals.

Molecular and cellular biochemistry·2009
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

Fredholm learning, a semisupervised learning framework, enhances algorithms using unlabeled data. This study investigates Fredholm kernel regularized classifiers, proving their generalization rate achieves O(1/n) for n labeled samples.

Area of Science:

  • Machine Learning
  • Integral Equations
  • Computational Mathematics

Background:

  • Fredholm learning offers a novel framework for semisupervised learning by solving regularized Fredholm integral equations.
  • This approach naturally integrates unlabeled data to enhance prediction performance in machine learning algorithms.
  • While algorithms and theoretical guarantees exist, the generalization ability of Fredholm kernel learning remains unexamined.

Purpose of the Study:

  • To investigate the generalization performance of Fredholm kernel regularized classifiers.
  • To analyze the learning rate and theoretical properties of these classifiers.
  • To provide a representer theorem for the Fredholm regularized scheme.

Main Methods:

  • Analysis of Fredholm kernel regularized classifiers.

Related Experiment Videos

  • Theoretical investigation of generalization bounds.
  • Derivation of a representer theorem.

    • Main Results:

    • The study proves that the learning rate for Fredholm kernel regularized classifiers can achieve O(1/n) in a limiting case, where n is the number of labeled samples.
    • A representer theorem is established for the proposed regularized scheme.
    • These findings provide theoretical insights into the generalization capabilities of Fredholm learning.

    Conclusions:

    • The generalization performance of Fredholm kernel learning is analyzed for the first time.
    • The established learning rate and representer theorem offer a foundation for understanding and applying Fredholm kernel regularized classifiers.
    • This work contributes to the theoretical understanding of semisupervised learning frameworks based on integral equations.