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

A model for nonpolynomial decrease in error rate with increasing sample size.

E Barnard1

  • 1Dept. of Electron. and Comput. Eng., Pretoria Univ.

IEEE Transactions on Neural Networks
|January 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

Consent and Chaperone Practices in Transvaginal Ultrasound: Exploring Sonographer Knowledge, Gender, and Ethical Challenges.

Irish medical journal·2026
Same author

Clinical, tactical and strategic benefits of a UK Spray Dried Plasma production capability.

BMJ military health·2025
Same author

Oral tranexamic acid as a preferred administration route for severe trauma in the extreme cold weather environment.

BMJ military health·2025
Same author

'Golden day' is a myth: rethinking medical timelines and risk in large scale combat operations.

BMJ military health·2024
Same author

Prehospital emergency care in a humanitarian environment: an overview of the ethical considerations.

BMJ military health·2023
Same author

Red cell haemolysis secondary to intraosseous (IO) blood transfusion in adult patients with major trauma: a systematic review.

BMJ military health·2023
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

Classifier error rates typically decrease with more training data. However, some studies show exponential error reduction, which this research attributes to finite problem sizes. A model demonstrates this rapid error decrease with sufficient samples.

Area of Science:

  • Machine Learning
  • Computational Statistics

Background:

  • Theoretical evidence suggests an inverse relationship between classifier error rate and training sample size.
  • Experimental studies by Cohn and Tesauro (1992) observed approximately exponential error rate decreases.

Purpose of the Study:

  • To investigate the cause of experimentally observed exponential error rate decreases in classifiers.
  • To demonstrate how finite problem characteristics influence learning curves.

Main Methods:

  • Analysis of theoretical evidence on classifier error rates.
  • Review of experimental findings on error rate reduction.
  • Development and analysis of a simple model classification problem.

Main Results:

Related Experiment Videos

  • The study provides evidence that finite problem sizes explain the observed exponential error rate decrease.
  • A model classification problem illustrates that error rates can approach zero exponentially or faster with sufficient training samples.

    • Conclusions:

    • The finite nature of studied problems is a key factor in observing exponential error rate decreases.
    • Understanding these finite effects is crucial for accurate interpretation of classifier performance and learning dynamics.