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

Singularities of Three-Layered Complex-Valued Neural Networks With Split Activation Function.

Masaki Kobayashi

    IEEE Transactions on Neural Networks and Learning Systems
    |April 20, 2017
    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

    Diabetic Polyneuropathy: New Strategies to Target Sensory Neurons in Dorsal Root Ganglia.

    International journal of molecular sciences·2023
    Same author

    MEK5-ERK5 Axis Promotes Self-renewal and Tumorigenicity of Glioma Stem Cells.

    Cancer research communications·2023
    Same author

    Chemical-state distributions in charged LiCoO<sub>2</sub> cathode particles visualized by soft X-ray spectromicroscopy.

    Scientific reports·2023
    Same author

    Predictors of life-space mobility in patients with fracture 3 months after discharge from convalescent rehabilitation ward: a prospective longitudinal study.

    Journal of physical therapy science·2023
    Same author

    Effect of multimodal comprehensive communication skills training with video analysis by artificial intelligence for physicians on acute geriatric care: a mixed-methods study.

    BMJ open·2023
    Same author

    5-Oxoproline Enhances 4-Hydroxytamoxifen-induced Cytotoxicity by Increasing Oxidative Stress in MCF-7 Breast Cancer Cells.

    Anticancer research·2023
    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

    In complex-valued neural networks (CVNNs) with biases, reducibility and nonminimality are distinct. This study reveals that minimality and singularity are independent concepts in these networks.

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Neural Networks

    Background:

    • Reducibility, nonminimality, and singularity are key concepts in neural network learning.
    • These concepts are equivalent in real-valued neural networks and bias-free complex-valued neural networks (CVNNs).
    • The behavior of CVNNs with biases is complex and less understood.

    Purpose of the Study:

    • To investigate the relationships between reducibility, nonminimality, and singularity in CVNNs with biases.
    • To clarify the distinctions and independencies among these learning concepts.
    • To provide examples illustrating exceptional reducibility.

    Main Methods:

    • Analysis of learning processes in complex-valued neural networks.
    • Mathematical investigation of reducibility, nonminimality, and singularity.

    Related Experiment Videos

  • Development of illustrative examples based on exceptional reducibility.

    • Main Results:

    • Exceptional reducibility was identified in CVNNs with biases.
    • Reducibility and nonminimality were shown to be distinct concepts.
    • Minimality and singularity were demonstrated to be independent.

    Conclusions:

    • The equivalence of reducibility, nonminimality, and singularity does not hold for CVNNs with biases.
    • Irreducibility in this context comprises minimality and exceptional reducibility.
    • The independence of minimality and singularity offers new insights into CVNN learning dynamics.