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

On-line learning in changing environments with applications in supervised and unsupervised learning.

Noboru Murata1, Motoaki Kawanabe, Andreas Ziehe

  • 1School of Science and Engineering, Waseda University, Tokyo, Japan.

Neural Networks : the Official Journal of the International Neural Network Society
|October 10, 2002
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

Towards robust foundation models for digital pathology.

Nature communications·2026
Same author

Beyond attention heatmaps: How to get better explanations for multiple instance learning models in histopathology.

Medical image analysis·2026
Same author

Prediction of an fMRI-based schizophrenia biomarker from EEG using dynamic functional connectivity: a simultaneous EEG-fMRI study.

Biomedical physics & engineering express·2026
Same author

AI-based discovery of functional boundaries in the human brain from intraoperative electrophysiology.

medRxiv : the preprint server for health sciences·2026
Same author

Modeling attention and binding in the brain through bidirectional recurrent gating.

Nature communications·2026
Same author

How simple can you go? An off-the-shelf transformer approach to molecular dynamics.

The Journal of chemical physics·2026
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 an adaptive online algorithm for continuous function learning without explicit loss functions. The method efficiently handles non-stationary data in unsupervised and supervised learning tasks.

Area of Science:

  • Machine Learning
  • Signal Processing
  • Adaptive Systems

Background:

  • Traditional machine learning often requires explicit loss functions and Hessian information.
  • Handling non-stationary environments and continuous function learning presents significant challenges.
  • The 'learning to learn' paradigm offers potential for more adaptive algorithms.

Purpose of the Study:

  • To propose and theoretically motivate an adaptive online algorithm.
  • To extend the 'learning to learn' concept for gradient flow-based learning.
  • To demonstrate the algorithm's applicability to diverse learning tasks, including those in non-stationary environments.

Main Methods:

  • Developed an adaptive online algorithm leveraging gradient flow information.

Related Experiment Videos

  • The algorithm operates without requiring explicit loss functions or Hessian matrices.
  • Applied the framework to unsupervised and supervised learning scenarios.

    • Main Results:

    • Demonstrated efficiency in blind separation of acoustic signals with drifting and switching non-stationarities.
    • Successfully applied to classification tasks using the US postal service dataset.
    • Showcased effectiveness in time-series prediction within changing environments.

    Conclusions:

    • The proposed algorithm offers a flexible approach for continuous function and distribution learning.
    • It effectively addresses challenges posed by non-stationary data and limited information.
    • The framework shows broad applicability across various machine learning domains.