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

Survival Tree01:19

Survival Tree

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 survival tree begins...
Multimachine Stability01:25

Multimachine Stability

Multimachine stability analysis is crucial for understanding the dynamics and stability of power systems with multiple synchronous machines. The objective is to solve the swing equations for a network of M machines connected to an N-bus power system.
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
Newton’s Method01:30

Newton’s Method

Newton’s Method is a powerful iterative technique for approximating the roots of real-valued, differentiable functions, particularly when analytical solutions are impractical. This approach is widely used in scientific computing, engineering, and finance, where equations may be too complex for traditional algebraic methods to handle. The method relies on an iterative process that refines an initial estimate using the function’s derivative to approach the true solution progressively.
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...

You might also read

Related Articles

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

Sort by
Same author

A Synthesis of 4-Quinolone <i>N</i>-Oxides and NMR Evidence of Their Protonation-Assisted Enolisation.

Molecules (Basel, Switzerland)·2026
Same author

Specialization of bat-fly interactions at different elevations in a montane forest of northern Peru.

Parasitology·2025
Same author

Modeling Brain Aging With Explainable Triamese ViT: Towards Deeper Insights Into Autism Disorder.

IEEE journal of biomedical and health informatics·2025
Same author

An Efficient Method for the Synthesis and In Silico Study of Novel Oxy-Camalexins.

Molecules (Basel, Switzerland)·2025
Same author

Transfer learning from inorganic materials to ivory detection.

Scientific reports·2025
Same author

Differential Evolution Algorithm for Fast Gains Learning in a High-Gain Controller.

IEEE transactions on neural networks and learning systems·2025
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

Related Experiment Videos

Uniformly stable backpropagation algorithm to train a feedforward neural network.

José de Jesús Rubio1, Plamen Angelov, Jaime Pacheco

  • 1Sección de Estudios de Posgrado e Investigación, Instituto Politécnico Nacional, Escuela Superior de Ingeniería Mecánica y Electrica Azcapotzalco, Distrito Federal 02250, Mexico. jrubioa@ipn.mx

IEEE Transactions on Neural Networks
|January 4, 2011
PubMed
Summary
This summary is machine-generated.

This study addresses the critical stability of discrete-time neural networks (NNs) for online processes. A novel backpropagation algorithm ensures uniform stability, eliminating overfitting and enabling reliable predictions in applications like warehouse load management.

Related Experiment Videos

Area of Science:

  • * Control Theory
  • * Machine Learning
  • * Artificial Intelligence

Background:

  • * Neural networks (NNs) are vital for online processes, yet their stability is often overlooked.
  • * Discrete-time systems, common in real-world applications, require specific stability analysis.
  • * Existing research primarily focuses on continuous-time NNs, neglecting discrete-time counterparts.

Purpose of the Study:

  • * To establish a theoretical framework for uniform stability in general discrete-time systems.
  • * To develop and validate a stable backpropagation (BP) algorithm for online identification.
  • * To demonstrate the practical application and stability of the proposed BP algorithm in warehouse load prediction.

Main Methods:

  • * Development and proof of a theorem for uniform stability in discrete-time systems.
  • * Modification of the backpropagation (BP) algorithm with a time-varying rate for enhanced stability.
  • * Comparative analysis of the proposed BP algorithm against Recursive Least Squares (RLS) and Kalman filters.

Main Results:

  • * A proven theorem guarantees uniform stability for general discrete-time systems.
  • * The modified BP algorithm achieves uniform stability for online identification, bounding identification error.
  • * The proposed algorithm effectively eliminates overfitting and demonstrates superior stability compared to fuzzy inference systems.

Conclusions:

  • * The novel time-varying backpropagation algorithm ensures uniform stability for discrete-time neural networks.
  • * This approach enhances reliability in online identification tasks and prevents overfitting.
  • * The algorithm shows promise for practical applications, such as predictive load management in warehouses.