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

Sensitivity-based adaptive learning rules for binary feedforward neural networks.

Shuiming Zhong, Xiaoqin Zeng, Shengli Wu

    IEEE Transactions on Neural Networks and Learning Systems
    |May 9, 2014
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    Feedback control systems01:26

    Feedback control systems

    800
    Feedback control systems are categorized in various ways based on their design, analysis, and signal types.
    Linear feedback systems are theoretical models that simplify analysis and design. These systems operate under the principle that their output is directly proportional to their input within certain ranges. For instance, an amplifier in a control system behaves linearly as long as the input signal remains within a specific range. However, most physical systems exhibit inherent nonlinearity...
    800

    You might also read

    Related Articles

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

    Sort by
    Same author

    Immune Biomarkers of Islet Transplant Rejection Revealed by Synthetic Immunological Niche.

    bioRxiv : the preprint server for biology·2026
    Same author

    Lifetime cumulative effect of reproductive factors, "Life's essential 8" health status and risk of chronic kidney disease: a nationwide prospective cohort study.

    BMC public health·2026
    Same author

    Age-stratified associations of glycemia, blood pressure, and cholesterol with mortality in diabetes: A prospective cohort study.

    BMC medicine·2026
    Same author

    Age-specific effects of hemoglobin A1c, blood pressure, and cholesterol levels on incident cardiovascular diseases among adults with diabetes in China: a 10-year prospective cohort study.

    Life metabolism·2026
    Same author

    Site-Specific Hydroxide Formation and Corrosion on Mg Nanocrystals.

    Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
    Same author

    Case Report: Ultrasound guided puncture for type 2 diabetes mellitus combined with psoas abscess-a report of two cases.

    Frontiers in medicine·2026
    Same journal

    Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

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

    CAFF-CIL: Causality-Aware Freedom Forgetting Approach for Class-Incremental Learning.

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

    Harmonic Autoencoding Framework for Multiple Tasks in Magnetic Particle Imaging Reconstruction.

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

    A Survey on Human-Centric Voice-Face Multimodal Learning.

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

    Vision-Assisted Foundation Model for Solving Multitask Vehicle Routing Problems.

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

    FP3O: Enabling Proximal Policy Optimization in Multiagent Cooperation With Parameter-Sharing Versatility.

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

    This study introduces adaptive learning rules for binary feedforward neural networks (BFNNs) using a sensitivity measure. The novel sensitivity-based adaptive learning algorithm (SBALR) improves learning performance over existing methods.

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Binary feedforward neural networks (BFNNs) are computationally efficient models.
    • BFNNs often face challenges in effective weight adaptation during training.
    • Existing learning algorithms may lead to suboptimal or destructive network adaptations.

    Purpose of the Study:

    • To propose novel adaptive learning rules for BFNNs.
    • To develop a sensitivity-based adaptive learning algorithm (SBALR).
    • To enhance the learning performance and stability of BFNNs.

    Main Methods:

    • Developed adaptive learning rules based on sensitivity analysis.
    • Incorporated the benefit, minimal disturbance, and burden-sharing principles.

    Related Experiment Videos

  • Designed neuron selection, weight adaptation, and learning control rules.
  • Implemented the Sensitivity-Based Adaptive Learning Algorithm (SBALR).

    • Main Results:

    • The SBALR algorithm demonstrated superior learning performance on benchmark datasets.
    • SBALR effectively guided constructive adaptations while avoiding destructive ones.
    • Experimental results showed better performance compared to Madaline rule II and backpropagation.

    Conclusions:

    • The proposed sensitivity-based adaptive learning rules offer an effective approach for BFNN training.
    • SBALR provides a robust and efficient method for improving BFNN learning.
    • This work contributes to the advancement of adaptive learning in neural networks.