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

Propagation of Action Potentials01:23

Propagation of Action Potentials

The propagation of an action potential refers to the process by which a nerve impulse, or "action potential," travels along a neuron.
Neurons (nerve cells) have a resting membrane potential, with a slightly negative charge inside compared to outside. This is maintained by ion channels, such as sodium (Na+) and potassium (K+) channels, which control the flow of ions. When a stimulus, like a touch or a signal from another neuron, triggers the neuron, sodium channels open, allowing sodium ions to...
Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
Fast Decoupled and DC Powerflow01:24

Fast Decoupled and DC Powerflow

The fast decoupled power flow method addresses contingencies in power system operations, such as generator outages or transmission line failures. This method provides quick power flow solutions, essential for real-time system adjustments. Fast decoupled power flow algorithms simplify the Jacobian matrix by neglecting certain elements, leading to two sets of decoupled equations:

You might also read

Related Articles

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

Sort by
Same author

Role of the postoperative subdural space and midline shift in predicting chronic subdural hematoma recurrence: A single-center study.

Surgical neurology international·2026
Same author

Risk Factors for Delayed Leptomeningeal Dissemination in Choroid Plexus Papillomas: A Systematic Review and Illustrative Case.

Current oncology (Toronto, Ont.)·2026
Same author

Unusual Brachial Plexus Injury Caused by a Personal Watercraft Fall.

Cureus·2026
Same author

The Art of Research and Scientific Writing in the Clinical Sciences: A Practical Guide.

Puerto Rico health sciences journal·2025
Same author

Cerebrospinal Fluid Density Measured Using Hounsfield Units on a Head CT Scan May Be Utilized as a Radiologic Indicator of Shunt Malfunction: A Pilot Study.

Cureus·2025
Same author

Prostate adenocarcinoma dural metastasis mimicking a subacute subdural hematoma.

Surgical neurology international·2025

Related Experiment Video

Updated: Jul 17, 2026

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
10:44

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Published on: December 7, 2021

Backpropagation algorithms for a broad class of dynamic networks.

Orlando De Jesús1, Martin T Hagan

  • 1Research Department, Halliburton Energy Services, Dallas, TX 75006, USA.

IEEE Transactions on Neural Networks
|February 7, 2007
PubMed
Summary

This study presents a Layered Digital Dynamic Network (LDDN) framework for dynamic neural networks. It enables efficient gradient and Jacobian computation using Backpropagation-Through-Time (BPTT) and Real-Time Recurrent Learning (RTRL) algorithms.

Related Experiment Videos

Last Updated: Jul 17, 2026

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
10:44

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline

Published on: December 7, 2021

Area of Science:

  • Computational Neuroscience
  • Machine Learning
  • Artificial Intelligence

Background:

  • Dynamic neural networks are crucial for modeling complex temporal data.
  • Efficient computation of gradients and Jacobians is essential for training these networks.
  • Existing frameworks may lack the flexibility to handle arbitrary dynamic network structures.

Purpose of the Study:

  • To introduce a general framework, the Layered Digital Dynamic Network (LDDN), for describing dynamic neural networks.
  • To develop and enable efficient implementations of gradient and Jacobian computation algorithms within this framework.
  • To compare the computational efficiency of Backpropagation-Through-Time (BPTT) and Real-Time Recurrent Learning (RTRL) for dynamic networks.

Main Methods:

  • Development of the Layered Digital Dynamic Network (LDDN) framework.
  • Implementation of general algorithms for gradient and Jacobian computation: Backpropagation-Through-Time (BPTT) and Real-Time Recurrent Learning (RTRL).
  • Analysis of the computational efficiency of BPTT and RTRL within the LDDN framework for arbitrary dynamic networks.

Main Results:

  • The LDDN framework provides a unified approach for dynamic neural network description.
  • Both BPTT and RTRL algorithms can be efficiently implemented using the LDDN framework.
  • BPTT demonstrates higher efficiency for gradient calculations, while RTRL is more efficient for Jacobian calculations.

Conclusions:

  • The LDDN framework offers a versatile and efficient platform for dynamic neural network research.
  • The choice between BPTT and RTRL depends on whether gradient or Jacobian computation is prioritized.
  • This work facilitates advancements in training and understanding complex dynamic neural systems.