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

New support vector algorithms

Scholkopf1, Smola, Williamson

  • 1GMD FIRST, Berlin, Germany.

Neural Computation
|July 25, 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

Odonto-Chirurgical Society: Some Remarks with Regard to Artificial Crowns.

The American journal of dental science·2019
Same author

Correspondence.

Colorectal disease : the official journal of the Association of Coloproctology of Great Britain and Ireland·2013
Same author

Newcastle-on-Tyne Infirmary: Practice of Sir John Fife.

Provincial medical journal and retrospect of the medical sciences·2011
Same author

A Successful Case of Trephining for Epilepsy, with Subsequent Resection of Trephine Opening.

British medical journal·2010
Same author

Report on Sixty-five Cases at the City of London Lying-in Hospital: Discussion.

Proceedings of the Royal Society of Medicine·2009
Same author

Patents alert

Phytotherapy research : PTR·2000
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

We introduce novel support vector algorithms for regression and classification that use a parameter nu to control support vectors. This approach simplifies the models by removing other parameters like epsilon or C.

Area of Science:

  • Machine Learning
  • Computational Statistics

Background:

  • Support Vector Machines (SVMs) are widely used for classification and regression.
  • Traditional SVMs involve parameters like epsilon (regression) and C (classification) that require careful tuning.
  • Controlling the number of support vectors is crucial for model efficiency and generalization.

Purpose of the Study:

  • To propose a new class of support vector algorithms.
  • To introduce a parameter nu for effective control over the number of support vectors.
  • To simplify SVMs by eliminating the need for other free parameters (epsilon or C).

Main Methods:

  • Development of novel support vector algorithms for both regression and classification tasks.
  • Introduction and theoretical analysis of the parameter nu.

Related Experiment Videos

  • Experimental validation of the proposed algorithms.

    • Main Results:

    • The parameter nu effectively controls the number of support vectors in the proposed algorithms.
    • The new parameterization allows for the elimination of the accuracy parameter epsilon in regression.
    • The new parameterization allows for the elimination of the regularization constant C in classification.
    • Experimental results demonstrate the efficacy of the new algorithms.

    Conclusions:

    • The proposed support vector algorithms offer a simplified yet effective approach to regression and classification.
    • The parameter nu provides a unified way to manage model complexity and performance.
    • These algorithms represent a valuable advancement in the field of machine learning.