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

Query-based learning applied to partially trained multilayer perceptrons.

J N Hwang1, J J Choi, S Oh

  • 1Dept. of Electr. Eng., Washington Univ., Seattle, WA.

IEEE Transactions on Neural Networks
|January 1, 1991
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

Observation of Charmonium Sequential Suppression in Heavy-Ion Collisions at the Relativistic Heavy Ion Collider.

Physical review letters·2026
Same author

Long-Range Transverse-Momentum Correlations and Radial Flow in Pb-Pb Collisions at the LHC.

Physical review letters·2026
Same author

Energy Independence of the Collins Asymmetry in p^{↑}p Collisions.

Physical review letters·2026
Same author

Limits on WIMP Dark Matter with NaI(Tl) Crystals in Three Years of COSINE-100 Data.

Physical review letters·2025
Same author

Normalized Raman Imaging for Studies of Tissue Physiology of the Kidney.

bioRxiv : the preprint server for biology·2025
Same author

Precision Measurement of Net-Proton-Number Fluctuations in Au+Au Collisions at RHIC.

Physical review letters·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

This study introduces a query-based learning method for neural networks, enhancing classification accuracy by refining decision boundaries. It significantly reduces the need for extensive training data compared to random sampling.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Neuroscience

Background:

  • Neural networks, particularly layered perceptrons, are widely used for classification tasks.
  • Binary classification involves assigning inputs to one of two categories based on a decision threshold.
  • Current training methods can be data-intensive, necessitating large datasets for optimal performance.

Purpose of the Study:

  • To present a novel query-based learning approach for neural networks.
  • To improve classification accuracy and efficiency in layered perceptrons.
  • To reduce the training set cardinality required for effective model training.

Main Methods:

  • An inversion algorithm was employed to generate the classification boundary of a partially trained perceptron.

Related Experiment Videos

  • Classification gradients were computed for boundary points to understand decision surface steepness.
  • Conjugate input pairs, guided by boundary and gradient information, were presented to an oracle for classification.

    • Main Results:

    • The proposed method effectively refines the classification boundary, leading to increased accuracy.
    • A significant reduction in the required training data size was observed compared to random data point generation.
    • The approach demonstrated practical utility in power system security assessment.

    Conclusions:

    • Query-based learning offers an efficient alternative to traditional neural network training methods.
    • The developed technique enhances classification performance by intelligently selecting informative training data.
    • This approach has potential applications in various domains requiring accurate and efficient classification.