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

Neural Circuits01:25

Neural Circuits

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...
Neuron Structure01:30

Neuron Structure

Neurons are the main type of cell in the nervous system that generate and transmit electrochemical signals. They primarily communicate with each other using neurotransmitters at specific junctions called synapses. Neurons come in many shapes that often relate to their function, but most share three main structures: an axon and dendrites that extend out from a cell body.
Structure and Function of Neurons
The neuronal cell body—the soma— houses the nucleus and organelles vital to cellular...
Neuron Structure01:31

Neuron Structure

Overview
Region of Convergence of Laplace Tarnsform01:20

Region of Convergence of Laplace Tarnsform

The Region of Convergence (ROC) is a fundamental concept in signal processing and system analysis, particularly associated with the Laplace transform. The ROC represents an area in the complex plane where the Laplace transform of a given signal converges, determining the transform's applicability and utility.
Consider a decaying exponential signal that begins at a specific time. When deriving its Laplace transform, the time-domain variable is replaced with a complex variable. This substitution...
Neuroplasticity01:01

Neuroplasticity

Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.

You might also read

Related Articles

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

Sort by
Same author

Correction: Targeted gene correction in the mdx mouse using short DNA fragments: towards application with bone marrow-derived cells for autologous remodeling of dystrophic muscle.

Gene therapy·2021
Same author

Construction of bacterial artificial chromosome (BAC/PAC) libraries.

Current protocols in human genetics·2008
Same author

Construction of bacterial artificial chromosome (BAC/PAC) libraries.

Current protocols in molecular biology·2008
Same author

Automated fault diagnosis in nonlinear multivariable systems using a learning methodology.

IEEE transactions on neural networks·2008
Same author

Identification of a haplosufficient 3.6-Mb region in human chromosome 11q14.3-->q21.

Cytogenetic and genome research·2002
Same author

Normal levels of soluble transferrin receptor in Friedreich ataxia.

Clinical genetics·2002

Related Experiment Videos

Learning and convergence analysis of neural-type structured networks.

M M Polycarpou1, P A Ioannou

  • 1Dept. of Electr. Eng.-Syst., Univ. of Southern California, Los Angeles, CA.

IEEE Transactions on Neural Networks
|January 1, 1992
PubMed
Summary

Structured networks offer a parallel approach to matrix algebra. Convergence analysis proves exponential weight convergence for solving linear equations and matrix inversion, with a new algorithm achieving exact convergence in one epoch.

Related Experiment Videos

Area of Science:

  • Computational mathematics
  • Artificial intelligence
  • Machine learning

Background:

  • Structured networks are a novel class of feedforward neural networks.
  • They are designed for solving matrix algebra problems using parallel computation.

Purpose of the Study:

  • To present a convergence analysis for training structured networks.
  • To explore convergence from numerical algebra and connectionist learning perspectives.
  • To investigate learning issues in structured networks.

Main Methods:

  • Convergence analysis of structured network training.
  • Development of learning rate bounds for exponential convergence.
  • Introduction of the orthogonalized back-propagation algorithm for specific problems.

Main Results:

  • Exponential convergence of weights is proved under specific learning rate bounds.
  • The analysis covers linear equation solving, matrix inversion, and Lyapunov equation solving.
  • The orthogonalized back-propagation algorithm ensures exact convergence in one epoch for a subset of problems.

Conclusions:

  • Structured networks provide an effective parallel method for matrix algebra.
  • The convergence analysis offers insights into both numerical algebra and neural network learning.
  • The proposed algorithm significantly enhances training efficiency for certain matrix problems.