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

A new classifier based on information theoretic learning with unlabeled data.

Kyu-Hwa Jeong1, Jian-Wu Xu, Deniz Erdogmus

  • 1Computational NeuroEngineering Laboratory, Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL 32611, USA. khjeong@cnel.ufl.edu

Neural Networks : the Official Journal of the International Neural Network Society
|August 17, 2005
PubMed
Summary

This study introduces an information theoretic learning (ITL) approach that uses unlabeled data during testing to enhance supervised learning classification. The novel method, based on density divergence minimization, shows potential for improving classifier performance in real-world applications.

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

Human-AI Cooperation in Healthcare and Rehabilitation.

Delaware journal of public health·2026
Same author

Temporal point process modeling of aggressive behavior onset in psychiatric inpatient youths with autism.

Scientific reports·2026
Same author

Training sparse convolutional deep predictive coding networks with attention.

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

Corticomorphic Hybrid CNN-SNN Architecture for EEG-Based Low-Footprint Low-Latency Auditory Attention Detection.

Annals of biomedical engineering·2026
Same author

Deep Learning-Based Prediction of Cardiopulmonary Disease in Retinal Images of Premature Infants.

JAMA ophthalmology·2026
Same author

A generative spike prediction model using behavioral reinforcement for re-establishing neural functional connectivity.

Nature computational science·2026

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Information Theory

Background:

  • Supervised learning traditionally uses fixed, labeled datasets for training and testing.
  • Exploiting unlabeled data during testing is an emerging area in machine learning for performance enhancement.

Purpose of the Study:

  • To present a novel information theoretic learning (ITL) approach for supervised learning.
  • To develop an extended training algorithm that incorporates unlabeled data during the testing phase.
  • To improve classification performance by minimizing density divergence.

Main Methods:

  • Utilized an information theoretic learning (ITL) framework.
  • Employed density divergence minimization as a core technique.
  • Developed a boosting-like algorithm with an ITL-based cost function for extended training.

Related Experiment Videos

Main Results:

  • Preliminary simulations indicate the proposed method's effectiveness.
  • The approach demonstrated potential for enhancing classifier performance during the application phase.
  • The integration of unlabeled data during testing showed promising outcomes.

Conclusions:

  • The ITL approach offers a new strategy for supervised learning by leveraging unlabeled data.
  • Density divergence minimization provides a robust mechanism for improving classification.
  • The extended training algorithm has the potential to boost classifier accuracy in practical scenarios.