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

Low rank updated LS-SVM classifiers for fast variable selection.

Fabian Ojeda1, Johan A K Suykens, Bart De Moor

  • 1Department of Electrical Engineering (ESAT-SCD division), Katholieke Universiteit Leuven, B-3001 Leuven, Belgium. fabian.ojeda@esat.kuleuven.be

Neural Networks : the Official Journal of the International Neural Network Society
|March 18, 2008
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

OGTFinder: A Curated Growth Temperature Data Set and Its Application To Predict Optimal Growth Temperatures of Bacteria and Archaea.

Journal of chemical information and modeling·2026
Same author

ADNEX-AI: automated extraction of ultrasound predictors for interpretable ovarian cancer risk stratification.

NPJ precision oncology·2025
Same author

A Novel Peak-Shape Aware Approach for Mass Alignment in Mass Spectrometry.

Rapid communications in mass spectrometry : RCM·2025
Same author

Artificial Intelligence Applied to Ultrasound Diagnosis of Pelvic Gynecological Tumors: A Systematic Review and Meta-Analysis.

Gynecologic and obstetric investigation·2025
Same author

Hemodynamic Monitoring During Hemodialysis Using Bioimpedance: A Comparison of Changes in Resistance Between Different Body Segments.

Hemodialysis international. International Symposium on Home Hemodialysis·2025
Same author

Clinical entity-aware domain adaptation in low resource setting for inflammatory bowel disease.

Frontiers in artificial intelligence·2025
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

This study introduces low-rank modifications for Least Squares Support Vector Machine (LS-SVM) classifiers, enabling efficient variable selection. The method offers reduced computational complexity and stable generalization error for machine learning tasks.

Area of Science:

  • Machine Learning
  • Computational Statistics

Background:

  • Least Squares Support Vector Machine (LS-SVM) classifiers are kernel methods solved via linear equations.
  • Efficient variable selection is crucial for optimizing machine learning models.

Purpose of the Study:

  • To present low-rank modifications for LS-SVM classifiers to enhance variable selection efficiency.
  • To develop a method for fast and efficient identification of relevant variables.

Main Methods:

  • Representing variable inclusion/exclusion as low-rank modifications to the LS-SVM kernel matrix (linear kernel).
  • Updating the LS-SVM solution instead of recomputing it for improved efficiency.
  • Utilizing a closed-form leave-one-out (LOO) error estimator for variable selection.

Related Experiment Videos

Main Results:

  • Demonstrated lower computational complexity compared to existing variable selection algorithms.
  • Achieved good stability in generalization error across benchmark and microarray datasets.
  • Efficiently updated LS-SVM solutions for streamlined variable selection.

Conclusions:

  • The proposed low-rank modification approach significantly improves the efficiency of variable selection in LS-SVM classifiers.
  • The method provides a computationally efficient and stable alternative for identifying relevant variables in machine learning.
  • Applicable to diverse datasets, including biological data from microarrays.