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

Clustering based on conditional distributions in an auxiliary space.

Janne Sinkkonen1, Samuel Kaski

  • 1Neural Networks Research Centre, Helsinki University of Technology, FIN-02015 HUT, Finland. janne.sinkkonen@hut.fi

Neural Computation
|December 19, 2001
PubMed
Summary

This study introduces a novel method for learning categories by analyzing relationships between primary and auxiliary data. The approach effectively clusters yeast gene expression data using biological functional classes as auxiliary information.

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

Machine learning on magnetoencephalography data yields generalizable low-dimensional neural fingerprints that distinguish individuals across task conditions.

bioRxiv : the preprint server for biology·2026
Same author

Misspecification-robust likelihood-free inference in high dimensions.

Computational statistics·2025
Same author

Towards modeling evolving longitudinal health trajectories with a transformer-based deep learning model.

Annals of epidemiology·2025
Same author

VitroBert: modeling DILI by pretraining BERT on in vitro data.

Journal of cheminformatics·2025
Same author

E-GuARD: expert-guided augmentation for the robust detection of compounds interfering with biological assays.

Journal of cheminformatics·2025
Same author

Molecular property prediction using pretrained-BERT and Bayesian active learning: a data-efficient approach to drug design.

Journal of cheminformatics·2025

Area of Science:

  • Computational biology
  • Machine learning
  • Data mining

Background:

  • Learning categories requires identifying local structures in primary data and homogeneity in associated auxiliary data.
  • Variation in auxiliary data provides meaningful insights into primary space features.

Purpose of the Study:

  • To develop a method for learning categories based on primary and auxiliary data.
  • To define categories in terms of the primary space while leveraging auxiliary data distributions.
  • To demonstrate the method's efficacy using yeast gene expression data.

Main Methods:

  • Minimizing Kullback-Leibler divergence-based distortion between conditional distributions of auxiliary data.
  • Employing an online algorithm similar to Hebb-type competitive learning.

Related Experiment Videos

  • Maximizing mutual information between learned categories and auxiliary data.

    • Main Results:

    • The developed method successfully clusters yeast gene expression data.
    • Biological knowledge of gene functional classes served as effective auxiliary data.
    • The approach links category learning to density estimation and distributional clustering.

    Conclusions:

    • The method provides a robust framework for category learning by integrating primary and auxiliary data.
    • This approach enhances the interpretability of clustering results by incorporating domain knowledge.
    • The study highlights the potential of this method for biological data analysis.