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

Discriminant component pruning. Regularization and interpretation of multi-layered back-propagation networks.

R A Koene1, Y Takane

  • 1Department of Psychology, McGill University, Montreal, Quebec H3A 1B1, Canada. randalk@marina.psych.mcgill.ca

Neural Computation
|March 23, 1999
PubMed
Summary

Discriminant Components Pruning (DCP) reduces neural network complexity while maintaining performance. This method aids in interpreting learned functions and improving generalization for classification tasks.

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

Regions of Significance in Multiple Regression Analysis.

Multivariate behavioral research·2016
Same author

Acceptance of evidence-supported hypotheses generates a stronger signal from an underlying functionally-connected network.

NeuroImage·2015
Same author

The vulnerability of skin grafts to allo- and xeno-antibodies.

Immunology today·2014
Same author

Functional connectivity reveals load dependent neural systems underlying encoding and maintenance in verbal working memory.

Neuroscience·2005
Same author

Should polycystic kidneys ever be used for renal transplantation?

Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association·2001
Same author

Evaluation of clinical guidelines for the management of end-stage renal disease in europe: the EU BIOMED 1 study.

Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association·2000

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Machine Learning

Background:

  • Neural networks are widely used for classification tasks.
  • Large neural networks can increase complexity, hindering interpretation and potentially reducing generalization.
  • Network pruning is a technique to manage complexity.

Purpose of the Study:

  • To introduce Discriminant Components Pruning (DCP), a novel method for pruning neural networks.
  • To demonstrate DCP's effectiveness in reducing network complexity.
  • To show DCP's utility in enhancing network interpretability and maintaining generalization performance.

Main Methods:

  • DCP prunes matrices of summed contributions between neural network layers.
  • The method focuses on reducing the rank of these matrices.

Related Experiment Videos

  • The study evaluates DCP's impact on generalization and interpretability.

    • Main Results:

    • DCP effectively reduces neural network complexity.
    • The pruning method maintains optimal generalization performance.
    • DCP proves useful for interpreting the functions learned by neural networks.

    Conclusions:

    • DCP is an effective technique for simplifying neural networks without sacrificing performance.
    • The method offers a valuable tool for network interpretation.
    • Future work may involve optimizing rank identification and incorporating nonlinear activation functions.