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

Pruning algorithms-a survey.

R Reed1

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

IEEE Transactions on Neural Networks
|January 1, 1993
PubMed
Summary
This summary is machine-generated.

Neural network pruning involves training larger networks and removing unnecessary parts. This approach optimizes generalization by finding the smallest effective system for the data, avoiding underfitting or slow learning.

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

Reirradiation Options for Previously Irradiated Prostate Cancer: Is It Feasible to Randomise Between Treatment With Stereotactic Body Radiotherapy (SBRT) Versus High-Dose-Rate Brachytherapy?

Clinical oncology (Royal College of Radiologists (Great Britain))·2026
Same author

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

Physical review letters·2026
Same author

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

Physical review letters·2025
Same author

Onset of Constituent Quark Number Scaling in Heavy-Ion Collisions at RHIC.

Physical review letters·2025
Same author

Measurement of In-Medium Jet Modification Using Direct Photon+Jet and π^{0}+Jet Correlations in p+p and Central Au+Au Collisions at sqrt[s_{NN}]=200  GeV.

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

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computer Science

Background:

  • Selecting the optimal system size for training is challenging.
  • Oversized systems may learn slowly and be sensitive to parameters.
  • Undersized systems fail to learn the data effectively.

Purpose of the Study:

  • To survey neural network pruning algorithms.
  • To present a method for optimizing neural network size.
  • To improve generalization in machine learning systems.

Main Methods:

  • Training neural networks larger than initially required.
  • Implementing algorithms to remove redundant network components.
  • Evaluating the impact of pruning on system performance.

Related Experiment Videos

Main Results:

  • Pruning allows for the identification of the smallest effective system.
  • This method addresses the challenge of determining optimal network size.
  • It offers a strategy to improve generalization in trained systems.

Conclusions:

  • Neural network pruning is an effective technique for optimizing generalization.
  • Training oversized networks followed by pruning is a viable strategy.
  • This approach mitigates issues associated with suboptimal system sizing.