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

An improved algorithm for neural network classification of imbalanced training sets.

R Anand1, K G Mehrotra, C K Mohan

  • 1Sch. of Comput. and Inf. Sci., Syracuse Univ., NY.

IEEE Transactions on Neural Networks
|January 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

Early radiographic accuracy and intra-operative parameters of patient-specific instrumentation versus conventional technique in knee osteotomies for adolescent deformity correction: A prospective comparative study.

Journal of clinical orthopaedics and trauma·2026
Same author

Correction: Performance of polyvinyl alcohol graphene oxide membrane for microplastic removal in wastewater with an IoT based monitoring approach.

Scientific reports·2026
Same author

Correction: Prediction of waste generation forecast and emission potential on the Erode City solid waste dump yards based on machine learning approach.

Scientific reports·2026
Same author

Airway Fire Prevention and Management in the Operating Room: A Mixed Methods Study on the Effectiveness of an Interprofessional Simulation-based Training Module.

Annals of African medicine·2026
Same author

Comparative evaluation and simulation of blockchain consensus mechanisms for secure and scalable peer to peer energy trading in microgrids.

Scientific reports·2025
Same author

Prediction of waste generation forecast and emission potential on the Erode City solid waste dump yards based on machine learning approach.

Scientific reports·2025
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

The backpropagation algorithm struggles with imbalanced datasets. A new method accelerates learning for two-class problems by optimizing error reduction for each class, improving convergence speed.

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Neural Networks

Background:

  • Backpropagation algorithm exhibits slow convergence for imbalanced two-class problems.
  • Dominant class error gradients overshadow smaller class error, hindering initial learning.
  • Slow convergence leads to inefficient training of neural networks.

Purpose of the Study:

  • To address the slow convergence of the backpropagation algorithm in imbalanced two-class classification.
  • To develop a modified technique for calculating weight-space directions that reduces error for both classes.
  • To accelerate the learning rate for imbalanced classification tasks.

Main Methods:

  • Analysis of the backpropagation algorithm's convergence behavior on imbalanced datasets.

Related Experiment Videos

  • Development of a modified error gradient calculation method.
  • Implementation of a new weight-space direction optimization technique.

    • Main Results:

    • Identified that the net error gradient is dominated by the larger class, increasing smaller class error initially.
    • The proposed modified technique calculates a weight-space direction that decreases error for each class.
    • The new algorithm accelerates the learning rate for two-class classification problems by an order of magnitude.

    Conclusions:

    • The modified backpropagation technique effectively overcomes slow convergence issues in imbalanced datasets.
    • This approach significantly enhances the efficiency of training neural networks for binary classification.
    • The method offers a substantial improvement in learning speed for machine learning models facing class imbalance.