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

Comparison of relevance learning vector quantization with other metric adaptive classification methods.

Th Villmann1, F Schleif, B Hammer

  • 1Clinic for Psychotherapy, University Leipzig, Karl-Tauchnitz-Str. 25, 04107 Leipzig, Germany. villmann@informatik.uni-leipzig.de

Neural Networks : the Official Journal of the International Neural Network Society
|December 14, 2005
PubMed
Summary

This study compares relevance learning in vector quantization and classification. It highlights differences in metric adaptation approaches for real-world datasets.

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

Evaluation of PD-1 and interleukin-10-receptor expression by T lymphocytes in malignant and benign pleural effusions.

Clinical and experimental medicine·2024
Same author

Evaluation of PD-1 T lymphocytes in bronchoalveolar lavage in lung cancer compared to benign lung diseases.

Clinical and experimental medicine·2023
Same author

Accelerating atomic structure search with cluster regularization.

The Journal of chemical physics·2018
Same author

Rotation and diffusion of naphthalene on Pt(111).

The Journal of chemical physics·2018
Same author

On-the-Fly Machine Learning of Atomic Potential in Density Functional Theory Structure Optimization.

Physical review letters·2018
Same author

Selection of conformational states in surface self-assembly for a molecule with eight possible pairs of surface enantiomers.

Chemical communications (Cambridge, England)·2016

Area of Science:

  • Machine Learning
  • Pattern Recognition
  • Data Classification

Background:

  • Relevance learning enhances machine learning by adapting distance metrics.
  • Existing metric adaptation methods offer alternatives to traditional relevance learning vector quantization (RLVQ).

Purpose of the Study:

  • To compare recent metric adaptation machine learning approaches with RLVQ variants.
  • To analyze the theoretical underpinnings and practical performance of these methods.

Main Methods:

  • Comparative analysis of theoretical motivations.
  • Empirical evaluation on diverse real-world datasets.
  • Benchmarking against relevance learning vector quantization variants.

Main Results:

Related Experiment Videos

  • Demonstrated distinct behavioral differences between various metric adaptation techniques.
  • Highlighted the impact of theoretical foundations on practical performance.
  • Quantified performance variations across multiple datasets.

Conclusions:

  • Understanding the theoretical basis is crucial for selecting appropriate metric adaptation methods.
  • RLVQ variants and other metric adaptation approaches show varied effectiveness depending on the dataset.
  • The study provides insights for optimizing classification and vector quantization strategies.