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

Supervised learning on large redundant training sets

M Møller1

  • 1Computer Science Department, Arhus University, Denmark.

International Journal of Neural Systems
|March 1, 1993
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

[Malnutrition in lung cancer patients : Influence of preoperative nutritional status on the postoperative outcome in patients with non-small cell lung cancer (NSCLC) after curative surgery].

Chirurgie (Heidelberg, Germany)·2026
Same author

Tailored nanophononic wavefield in a patterned bilayer system probed by ultrafast convergent beam electron diffraction.

Structural dynamics (Melville, N.Y.)·2025
Same author

Self-assembling supramolecular columnar organogels formed by wedge shaped cesium 3,4,5-alkyloxy benzene sulfonates.

Soft matter·2025
Same author

The Effect of an 8-Week Low- or High-Volume Protocol of the Adductor Strengthening Programme on Hip Adduction Strength in Female Football Players-A Randomized Trial.

Scandinavian journal of medicine & science in sports·2025
Same author

Handball playing volume and knee injury risk in youth handball: the influence of sex.

Journal of science and medicine in sport·2025
Same author

Outcome, severity of injury and length of sick leave after an ankle fracture: an observational register study.

Acta orthopaedica Belgica·2025
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

A new algorithm enhances supervised learning efficiency on large datasets. It ensures computation per weight update is independent of training set size, unlike traditional methods.

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Optimization Algorithms

Background:

  • Supervised learning on large, redundant datasets presents computational challenges.
  • Standard offline algorithms (e.g., conjugate gradient) scale poorly with dataset size.
  • Online algorithms (e.g., stochastic backpropagation) offer better scalability but may lack convergence properties.

Purpose of the Study:

  • To introduce a novel algorithm for efficient supervised learning.
  • To address the computational scaling limitations of existing methods with large training sets.
  • To combine the benefits of both offline and online learning paradigms.

Main Methods:

  • Development of a new supervised learning algorithm.
  • Analysis of computational complexity concerning weight updates and training set size.

Related Experiment Videos

  • Comparison with standard conjugate gradient and stochastic backpropagation algorithms.

    • Main Results:

    • The proposed algorithm achieves computational cost per weight update independent of training set size.
    • It integrates desirable characteristics of both offline and online learning approaches.
    • Demonstrates improved efficiency for large-scale supervised learning tasks.

    Conclusions:

    • The new algorithm offers an efficient solution for supervised learning on large, redundant datasets.
    • It overcomes the scalability limitations of traditional offline methods.
    • Represents a significant advancement in optimizing computational efficiency for machine learning.