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 Concept Videos

Singularity Functions for Shear01:26

Singularity Functions for Shear

477
In structural analysis, singularity functions are crucial in simplifying the representation of shear forces in beams under discontinuous loading. These functions describe discontinuous  variations in shear force across a beam with varying loads by using a single mathematical expression, regardless of the complexity of the loading conditions. The singularity functions are derived from creating a free-body diagram of the beam and then making conceptual cuts at specific points to examine the...
477
Neural Circuits01:25

Neural Circuits

3.1K
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...
3.1K
Survival Tree01:19

Survival Tree

463
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
463

You might also read

Related Articles

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

Sort by
Same author

Sequential Learning on sEMGs in Short- and Long-term Situations via Self-training Semi-supervised Support Vector Machine.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2022
Same author

Hyperbolic Gradient Operator and Hyperbolic Back-Propagation Learning Algorithms.

IEEE transactions on neural networks and learning systems·2017
Same author

Learning dynamics of a single polar variable complex-valued neuron.

Neural computation·2015
Same author

Performance Bounds of Quaternion Estimators.

IEEE transactions on neural networks and learning systems·2015
Same author

Local minima in hierarchical structures of complex-valued neural networks.

Neural networks : the official journal of the International Neural Network Society·2013
Same author

The uniqueness theorem for complex-valued neural networks with threshold parameters and the redundancy of the parameters.

International journal of neural systems·2008

Related Experiment Video

Updated: Mar 18, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.2K

Resolution of Singularities Introduced by Hierarchical Structure in Deep Neural Networks.

Tohru Nitta

    IEEE Transactions on Neural Networks and Learning Systems
    |July 9, 2016
    PubMed
    Summary

    This study introduces deep neural network models without critical points, improving gradient-based optimization. We provide methods to create these networks, enhancing training stability and performance.

    More Related Videos

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    853
    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
    12:27

    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

    Published on: February 15, 2017

    7.4K

    Related Experiment Videos

    Last Updated: Mar 18, 2026

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    1.2K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    853
    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations
    12:27

    Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

    Published on: February 15, 2017

    7.4K

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Deep Learning Theory

    Background:

    • Deep neural networks (DNNs) often suffer from critical points hindering gradient-based optimization.
    • The hierarchical structure of DNNs introduces numerous critical points, particularly along straight lines dependent on network architecture.

    Purpose of the Study:

    • To theoretically analyze singular points in artificial deep neural networks.
    • To develop DNN models inherently free of critical points for improved optimization.
    • To provide practical methods for achieving critical-point-free DNNs.

    Main Methods:

    • Theoretical analysis of singular points in deep neural networks.
    • Derivation of a sufficient condition for DNNs lacking critical points.
    • Investigation of weight matrix rank and regularity's role in critical point existence.
    • Development of novel learning algorithms and network architectures.

    Main Results:

    • Demonstrated existence of numerous critical points in DNNs related to their hierarchical structure.
    • Derived a general sufficient condition to eliminate critical points in DNNs.
    • Established a link between critical points and the rank/regularity of weight matrices.
    • Introduced an "avoidant learning algorithm" and "avoidant neural network" architecture.

    Conclusions:

    • Deep neural networks can be designed to be free of critical points, enhancing gradient-based optimization.
    • The proposed methods offer practical solutions for developing more optimizable DNNs.
    • This work contributes to the theoretical understanding and practical implementation of stable deep learning models.