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 formal selection and pruning algorithm for feedforward artificial neural network optimization.

P S Ponnapalli, K C Ho, M Thomson

    IEEE Transactions on Neural Networks
    |February 7, 2008
    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

    Robust Ellipse Fitting Based on Maximum Correntropy Criterion With Variable Center.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2023
    Same author

    Approaches to characterizing oscillatory burst detection algorithms for electrophysiological recordings.

    Journal of neuroscience methods·2023
    Same author

    Classification of Brainwaves Using Convolutional Neural Network.

    Proceedings of the ... European Signal Processing Conference (EUSIPCO). EUSIPCO (Conference)·2022
    Same author

    Non-Invasive Heart Rate Estimation From Ballistocardiograms Using Bidirectional LSTM Regression.

    IEEE journal of biomedical and health informatics·2021
    Same author

    Robust Ellipse Fitting With Laplacian Kernel Based Maximum Correntropy Criterion.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2021
    Same author

    Life cycle assessment (LCA) of electrically-enhanced POME filtration: Environmental impacts of conductive-membrane formulation and process operating parameters.

    Journal of environmental management·2020
    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 an improved pruning technique for artificial neural networks (ANNs) that enhances model efficiency and generalization. The method effectively reduces network complexity while maintaining performance on various nonlinear systems.

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Computational Neuroscience

    Background:

    • Feedforward artificial neural networks (ANNs) are powerful tools for modeling complex systems.
    • The backpropagation training algorithm is a standard method for training ANNs.
    • Network pruning is crucial for reducing complexity and improving generalization.

    Discussion:

    • A novel selection and pruning technique is proposed for feedforward ANNs, utilizing the local relative sensitivity index.
    • This technique focuses on parallel pruning of redundant weights within network subgroups.
    • The theoretical underpinnings of this improved pruning method are detailed, building upon the backpropagation algorithm.

    Key Insights:

    • The enhanced pruning technique demonstrates superior performance compared to existing methods.

    Related Experiment Videos

  • Achieved improvements include significant reduction in model residues and enhanced generalization capabilities.
  • The method effectively reduces overall network complexity, leading to more efficient models.

    • Outlook:

    • The effectiveness of this pruning strategy is validated across diverse nonlinear systems.
    • Applications include the three-bit parity problem, Van der Pol equation, chemical processes, and discrete-time systems.
    • Future work may involve exploring this technique in deeper or recurrent neural network architectures.