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 information criterion for optimal neural network selection.

D B Fogel1

  • 1Orincon Corp., San Diego, CA.

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

A step toward computer-assisted mammography using evolutionary programming and neural networks.

Cancer letters·2008
Same author

Evolving neural networks to play checkers without relying on expert knowledge.

IEEE transactions on neural networks·2008
Same author

Multiple-vector self-adaptation in evolutionary algorithms.

Bio Systems·2001
Same author

Do evolutionary processes minimize expected losses?

Journal of theoretical biology·2000
Same author

Fitness distributions in evolutionary computation: motivation and examples in the continuous domain.

Bio Systems·2000
Same author

Rapid automated molecular replacement by evolutionary search.

Acta crystallographica. Section D, Biological crystallography·1999
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

Selecting the best neural network design is crucial. A modified Akaike

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Statistical Modeling

Background:

  • Choosing optimal neural network architectures is a significant challenge in machine learning.
  • Existing methods often lack objective criteria for network selection.
  • Statistical model identification principles offer a potential framework for network design.

Purpose of the Study:

  • To address the problem of selecting an optimal neural network design.
  • To establish a relationship between optimal network design and statistical model identification.
  • To introduce a novel information statistic for objective network selection.

Main Methods:

  • Describing a relationship between optimal network design and statistical model identification.
  • Presenting a derivative of Akaike's Information Criterion (AIC).

Related Experiment Videos

  • Developing an information statistic for network selection.

    • Main Results:

    • An information statistic derived from a modified AIC is proposed.
    • This statistic enables objective selection of the best neural network for binary classification.
    • The proposed technique demonstrates extensibility to multi-class problems.

    Conclusions:

    • The modified AIC provides an objective method for selecting optimal neural networks.
    • This approach enhances the reliability of neural network design for classification tasks.
    • The method is adaptable for various classification problem complexities.