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

Linearization and Approximation01:26

Linearization and Approximation

154
Linearization is a mathematical technique used to approximate complex, nonlinear functions with simpler linear models in the vicinity of a chosen reference point. The method is based on the idea that, although a function may be difficult to evaluate exactly, its behavior near a specific input value can often be closely approximated by the tangent line at that point. This approach is particularly useful when small deviations from a known value are involved.Consider the square root function, for...
154
Linear Approximation in Frequency Domain01:26

Linear Approximation in Frequency Domain

423
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....
423
Introduction to One-to-one Functions01:23

Introduction to One-to-one Functions

290
A one-to-one function is a mathematical function in which each element of the domain maps to a distinct and unique element in the range. This property ensures that no two different inputs result in the same output, formally expressed as f (x1) ≠ f (x2) whenever x1 ≠ x2. The graphical criterion for identifying such functions is the Horizontal Line Test, which indicates that a function is one-to-one if and only if no horizontal line intersects its graph at more than one point.A...
290
Linear Approximation in Time Domain01:21

Linear Approximation in Time Domain

394
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,...
394
Approximate Integration01:24

Approximate Integration

95
In many practical and theoretical contexts, the exact value of a definite integral may be inaccessible. This limitation typically arises when the antiderivative of a function is either unknown or cannot be expressed in a closed mathematical form. Alternatively, it can occur when a function is defined not by a formula but by a finite set of empirical data points, such as those collected during experiments. In these cases, approximate integration techniques provide a valuable solution.One of the...
95
Newton’s Method01:30

Newton’s Method

120
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.
120

You might also read

Related Articles

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

Sort by
Same author

Addressing common misinterpretations of KART and UAT in neural network literature.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

On the Kolmogorov neural networks.

Neural networks : the official journal of the International Neural Network Society·2024
Same author

On the approximation by single hidden layer feedforward neural networks with fixed weights.

Neural networks : the official journal of the International Neural Network Society·2018
See all related articles

Related Experiment Videos

A Single Hidden Layer Feedforward Network with Only One Neuron in the Hidden Layer Can Approximate Any Univariate

Namig J Guliyev1, Vugar E Ismailov2

  • 1njguliyev@gmail.com.

Neural Computation
|May 13, 2016
PubMed
Summary

This study constructs a novel sigmoidal activation function for single-hidden-layer neural networks. This function enables accurate approximation of continuous functions using minimal network complexity.

Related Experiment Videos

Area of Science:

  • Computational mathematics
  • Artificial intelligence
  • Neural network theory

Background:

  • Feedforward neural networks with sigmoidal activation functions can approximate continuous functions.
  • Approximation capabilities are typically dependent on an unlimited number of hidden neurons.
  • Previous research focused on networks with extensive hidden layers.

Purpose of the Study:

  • To investigate constructive approximation using neural networks with a single hidden neuron.
  • To develop a novel, smooth, sigmoidal, and almost monotone activation function.
  • To achieve arbitrary accuracy in function approximation with minimal network architecture.

Main Methods:

  • Algorithmic construction of a specialized activation function.
  • Utilizing a single neuron in the hidden layer of a feedforward neural network.
  • Developing a computer program to compute the activation function's values.

Main Results:

  • A novel activation function, [Formula: see text], was algorithmically constructed.
  • The function allows for accurate approximation of any continuous function on finite intervals.
  • The method requires only one neuron in the hidden layer.
  • The algorithm is implemented in a functional computer program.

Conclusions:

  • Efficient function approximation is achievable with a single hidden layer neuron.
  • The developed activation function provides a powerful tool for constructive approximation.
  • This approach offers a more parsimonious neural network architecture for function approximation.