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 Hybrid Constructive Algorithm for Single-Layer Feedforward Networks Learning.

Xing Wu, Paweł Rózycki, Bogdan M Wilamowski

    IEEE Transactions on Neural Networks and Learning Systems
    |September 13, 2014
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    Neural Circuits01:25

    Neural Circuits

    3.0K
    Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
    Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
    3.0K
    Linear Approximation in Frequency Domain01:26

    Linear Approximation in Frequency Domain

    501
    Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
    In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
    501

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Smart utilisation of reverse solute diffusion in forward osmosis for water treatment: A mini review.

    The Science of the total environment·2023
    Same author

    High-sensitivity low-noise photodetector using a large-area silicon photomultiplier.

    Optics express·2023
    Same author

    Research progress on substitution of <i>in vivo</i> method(s) by <i>in vitro</i> method(s) for human vaccine potency assays.

    Expert review of vaccines·2023
    Same author

    Adapting ecosystem restoration for sustainable development in a changing world.

    Innovation (Cambridge (Mass.))·2023
    Same author

    An Efficiently Doped PEDOT:PSS Ink Formulation via Metastable Liquid-Liquid Contact for Capillary Flow-Driven, Hierarchically and Highly Conductive Films.

    Small (Weinheim an der Bergstrasse, Germany)·2023
    Same author

    Improving Electroluminescence Efficiency by Linear Polar Host Capable of Promoting Horizontal Dipole Orientation for Dopant.

    Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2022
    Same journal

    Granular Ball-Based Noise-Resistant Fuzzy Multineighborhood Feature Selection via Label Enhancement and Feature Graph.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Fighting Evolving Spam With ARTMAP Models: A Noise-Resilient Online Detection Framework.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    HyperSAT: Unsupervised Hypergraph Neural Networks for Weighted MaxSAT Problems.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Negation of Basic Belief Assignment in Multisource Information Fusion on Dempster-Shafer Theory With Applications in Pattern Classification.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Intervention Feasible Region and Driver Risk Capacity Aware Human-Machine Collaborative Safe Trajectory Planning.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    A Unified Differential Denoising Learning Framework With a Pre-Trained Model and Fuzzy Graph Networks for Drug-Drug Interaction Prediction.

    IEEE transactions on neural networks and learning systems·2026
    See all related articles

    A novel hybrid constructive (HC) algorithm efficiently trains single-layer feedforward networks (SLFNs), simultaneously determining network size and parameters. This method outperforms trial-and-error approaches, yielding more compact SLFNs for classification and regression tasks.

    Area of Science:

    • Machine Learning
    • Artificial Intelligence
    • Neural Networks

    Background:

    • Single-layer feedforward networks (SLFNs) are universal approximators used in classification and regression.
    • SLFN learning requires determining network size and training parameters, which current algorithms struggle to optimize simultaneously.
    • Existing methods often involve preset network sizes or inefficient trial-and-error for size optimization.

    Purpose of the Study:

    • To propose a hybrid constructive (HC) algorithm for simultaneous SLFN parameter training and network size determination.
    • To develop an efficient SLFN learning method that avoids costly trial-and-error processes.
    • To achieve more compact and efficiently trained SLFNs compared to existing algorithms.

    Main Methods:

    • A hybrid algorithm combining Levenberg-Marquardt and least-square methods for training SLFNs with a fixed size.

    Related Experiment Videos

  • An incremental constructive scheme that adds neurons when training gets stuck in local minima.
  • Continued training on previous results after adding new neurons for efficiency.

    • Main Results:

    • The HC algorithm trains all parameters and determines network size concurrently.
    • It demonstrates higher efficiency compared to optimization methods relying on trial and error.
    • The proposed method achieves significantly more compact SLFNs than traditional construction algorithms.

    Conclusions:

    • The HC algorithm offers an efficient and effective solution for SLFN learning.
    • It addresses the limitations of existing methods in simultaneously optimizing network size and parameters.
    • The HC algorithm provides a more computationally efficient and compact SLFN model for practical applications.