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

Accelerated learning by active example selection

B T Zhang1

  • 1AI Division, Institute for Computer Science, University of Bonn, Germany.

International Journal of Neural Systems
|March 1, 1994
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

First Detection of Ultrahigh Energy Emission from Gamma-Ray Binary LS I +61° 303.

Physical review letters·2026
Same author

[Key updates in the 16th edition of the japanese classification of gastric carcinoma].

Zhonghua wei chang wai ke za zhi = Chinese journal of gastrointestinal surgery·2026
Same author

Evidence of Cosmic-Ray Acceleration up to Sub-PeV Energies in the Supernova Remnant IC 443.

Physical review letters·2026
Same author

Precise Measurement of the Cosmic Ray Helium Spectrum above 0.1 PeV.

Physical review letters·2026
Same author

All-Sky Search for Individual Primordial Black Hole Bursts with LHAASO.

Physical review letters·2025
Same author

Experimental Limits on Solar Reflected Dark Matter with a New Approach on Accelerated-Dark-Matter-Electron Analysis in Semiconductors.

Physical review letters·2024
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

This study introduces an incremental learning algorithm for neural networks that selects critical training examples. This approach enhances training speed and generalization performance compared to traditional methods.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Traditional neural network training often uses the backpropagation algorithm with all training examples.
  • Existing methods focus on sophisticated weight modification rules for faster training.
  • Sequencing of training examples can be random or predetermined in conventional approaches.

Purpose of the Study:

  • To investigate an alternative training approach for multilayer neural networks.
  • To develop a method that improves training speed and generalization performance.
  • To present an incremental learning algorithm based on example criticality.

Main Methods:

  • Deriving a measure of example criticality.
  • Implementing an incremental learning algorithm that selects a critical subset of training data.

Related Experiment Videos

  • Utilizing a progressively increasing training set size.

    • Main Results:

    • The proposed method significantly improves training speed.
    • Enhanced generalization performance was observed in real-world applications.
    • The approach is compatible with gradient descent variations.

    Conclusions:

    • Incremental learning by selecting critical examples offers a viable alternative to conventional neural network training.
    • The criticality measure effectively identifies essential training data for improved efficiency.
    • This method holds promise for optimizing neural network performance across various applications.