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

Modeling with Differential Equations01:25

Modeling with Differential Equations

227
Population dynamics can be described mathematically by considering the population size P(t) as a function of time. The rate of change of the population is then represented by the derivative of P(t). A simple assumption is that the rate of growth is proportional to the size of the population itself. This leads to an exponential growth model, where the population increases rapidly without bound. While this is a useful first approximation, it does not reflect realistic long-term...
227
Linear Approximation in Frequency Domain01:26

Linear Approximation in Frequency Domain

432
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
432
Linear Approximation in Time Domain01:21

Linear Approximation in Time Domain

406
Nonlinear systems often require sophisticated approaches for accurate modeling and analysis, with state-space representation being particularly effective. This method is especially useful for systems where variables and parameters vary with time or operating conditions, such as in a simple pendulum or a translational mechanical system with nonlinear springs.
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
406
Introduction to Differential Equations01:20

Introduction to Differential Equations

288
A differential equation is a mathematical expression that establishes a relationship between a function and its derivatives. These equations are fundamental in modeling dynamic systems across various fields of science and engineering. The order of a differential equation is defined by the highest order derivative present in the equation. A first-order differential equation includes only the first derivative, while a second-order differential equation includes up to the second derivative of the...
288
Differential Equations: Problem Solving01:21

Differential Equations: Problem Solving

173
When analyzing the motion of falling objects, it is essential to consider not only the force of gravity but also the opposing force of air resistance. A practical example involves releasing a heavy test weight during a safety check on a ship. As the weight falls from rest, gravity accelerates it downward while air resistance exerts an upward force that increases with velocity. This dynamic interplay of forces is well described by differential equations, which provide a mathematical framework...
173
Poisson's And Laplace's Equation01:25

Poisson's And Laplace's Equation

4.6K
The electric potential of the system can be calculated by relating it to the electric charge densities that give rise to the electric potential. The differential form of Gauss's law expresses the electric field's divergence in terms of the electric charge density.
4.6K

You might also read

Related Articles

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

Sort by
Same author

Local Surrogate Models With Residual Fuzzy Rules for Model-Agnostic Explanations.

IEEE transactions on cybernetics·2026
Same author

A Prediction Model Integrating Adaptive-Network-Based Fuzzy Inference System and Fuzzy C-Mean Clustering.

IEEE transactions on cybernetics·2026
Same author

Individual Linguistic Granular Computing: A Granulation-Degranulation-Based Approach.

IEEE transactions on cybernetics·2026
Same author

S<sup>2</sup>FS: Spatially-Aware Separability-Driven Feature Selection in Fuzzy Decision Systems.

IEEE transactions on neural networks and learning systems·2026
Same author

Data-Driven Cation Engineering Guides Electrolyte Design for Sustainable Aqueous Zinc Battery Chemistries.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

A complex-valued widening spiking neural network.

Neural networks : the official journal of the International Neural Network Society·2026

Related Experiment Video

Updated: Mar 30, 2026

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches
10:50

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

Published on: June 21, 2022

2.3K

Constructing general partial differential equations using polynomial and neural networks.

Ladislav Zjavka1, Witold Pedrycz2

  • 1VŠB-Technical University of Ostrava, Faculty of Electrical Engineering and Computer Science, Department of Computer Science, 17. listopadu 15/2172 Ostrava, Czech Republic.

Neural Networks : the Official Journal of the International Neural Network Society
|November 9, 2015
PubMed
Summary

Differential polynomial neural networks approximate complex functions using polynomial terms and derivatives. This novel approach enables solving partial differential equations from data, advancing function approximation and real-world problem-solving.

Keywords:
Differential polynomial neural networkGeneral partial differential equation compositionMulti-variable function approximationSum derivative term substitution

Related Experiment Videos

Last Updated: Mar 30, 2026

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches
10:50

Computational Modeling of Retinal Neurons for Visual Prosthesis Research - Fundamental Approaches

Published on: June 21, 2022

2.3K

Area of Science:

  • Computational Mathematics
  • Artificial Intelligence
  • Numerical Analysis

Background:

  • Traditional methods approximate multi-variable functions using discrete observations and polynomial relations.
  • Artificial neural networks (ANNs) use weighted sums for pattern similarity, but struggle with complex functions.
  • Partial differential equations (PDEs) define many real-world phenomena but can be challenging to solve directly from data.

Purpose of the Study:

  • Introduce a new class of neural networks: Differential Polynomial Neural Networks (DPNNs).
  • Develop a method to construct and solve unknown PDEs from data using polynomial approximations.
  • Enhance function approximation capabilities for complex and periodic functions.

Main Methods:

  • DPNNs utilize non-linear multi-variable composite polynomials to represent function relationships.
  • Network layers generate polynomial terms that approximate partial derivative changes of input variables.
  • Sigmoidal activation functions are employed to refine polynomial term approximations for complex functions.

Main Results:

  • DPNNs successfully decompose generalized partial derivative data relations into multi-layer polynomial structures.
  • The network demonstrates the ability to approximate complicated periodic functions beyond the capacity of simple polynomials.
  • Similarity analysis facilitates substitutions for differential equations and dimensional unit formation from data.

Conclusions:

  • Differential Polynomial Neural Networks offer a novel approach to solving PDEs and approximating complex functions.
  • This method integrates data-driven regression with polynomial representations for enhanced analytical capabilities.
  • DPNNs have potential applications in modeling and solving diverse real-world problems described by differential equations.