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

Linear Approximation in Time Domain01:21

Linear Approximation in Time Domain

155
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,...
155
Linear Approximation in Frequency Domain01:26

Linear Approximation in Frequency Domain

180
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....
180
Accuracy, limits, and approximation01:28

Accuracy, limits, and approximation

886
Accuracy, limits, and approximations are common in many fields, especially in engineering calculations. These concepts are imperative for ensuring that a given value is as close as possible to its true value.
Accuracy is defined as the closeness of the measured value to the true or actual value. In engineering mechanics, repeated measurements are taken during theoretical or experimental analyses to ensure that the result is precise and accurate.
The accuracy of any solution is based on the...
886
Inverse z-Transform by Partial Fraction Expansion01:20

Inverse z-Transform by Partial Fraction Expansion

454
The inverse z-transform is a crucial technique for converting a function from its z-domain representation back to the time domain. One effective method for finding the inverse z-transform is the Partial Fraction Method, which involves decomposing a function into simpler fractions with distinct coefficients. These fractions correspond to known z-transform pairs, facilitating the inverse transformation process.
To begin the process, the poles of the function are identified and the function is...
454
Mason's Rule01:20

Mason's Rule

588
Mason's rule is a powerful tool in control systems and signal processing. It simplifies the calculation of transfer functions from signal-flow graphs. This method leverages various elements, including loop gains, forward-path gains, and non-touching loops, to determine the transfer function efficiently.
Loop gain is determined by identifying and tracing a path from a node back to itself. This involves computing the product of branch gains along the loop. Each loop's gain is crucial for...
588
Residuals and Least-Squares Property01:11

Residuals and Least-Squares Property

8.1K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
8.1K

You might also read

Related Articles

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

Sort by
Same author

Mitigating the Drawbacks of the L<sub>0</sub> Norm and the Total Variation Norm.

Axiomsยท2025
Same author

Deterministic Versus Nondeterministic Optimization Algorithms for the Restricted Boltzmann Machine.

Journal of computational and cognitive engineeringยท2024
Same author

Photon Starvation Artifact Reduction by Shift-Variant Processing.

IEEE access : practical innovations, open solutionsยท2022
Same author

Estimation of the Initial Image's Contributions to the Iterative Landweber Reconstruction.

IEEE transactions on radiation and plasma medical sciencesยท2021
Same author

Filtered backprojection implementation of the immediately-after-backprojection filtering.

Biomedical physics & engineering expressยท2020
Same author

Real-time selection of iteration number.

Biomedical physics & engineering expressยท2020
Same journal

A Multi-Head Attention Transformer Model for Wearable in Situ Fall Detection.

IEEE access : practical innovations, open solutionsยท2026
Same journal

Validating Single-Camera Pose Estimation Against Multi-Camera Motion Capture for Accessible Biomechanical Assessment.

IEEE access : practical innovations, open solutionsยท2026
Same journal

Learning to Diagnose Privately: DP-Powered LLMs for Radiology Report Classification.

IEEE access : practical innovations, open solutionsยท2026
Same journal

Radio-Frequency Toroid Susceptometry of Magnetic Nanoparticles: What Goes Around Comes Around.

IEEE access : practical innovations, open solutionsยท2026
Same journal

Cross-Architecture Knowledge Distillation for Histopathological Image Analysis.

IEEE access : practical innovations, open solutionsยท2026
Same journal

Mislabel Identification Using Transfer Learning-Based Ensemble Method.

IEEE access : practical innovations, open solutionsยท2026
See all related articles

Related Experiment Video

Updated: Oct 19, 2025

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
06:45

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Published on: October 28, 2022

1.8K

A Deep-Network Piecewise Linear Approximation Formula.

Gengsheng L Zeng1

  • 1Department of Computer Science, Utah Valley University, Orem, UT 84058, USA; Department of Radiology and Imaging Sciences, The University of Utah, Salt Lake City, UT 84108, USA.

IEEE Access : Practical Innovations, Open Solutions
|September 17, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces a novel deep learning architecture and weight calculation formula, eliminating the need for training. This method guarantees optimal weights for universal function approximation, matching shallow interpolation results.

Keywords:
Approximation algorithmsartificial neural networksfunction approximationinterpolationmulti-layer neural network

Related Experiment Videos

Last Updated: Oct 19, 2025

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator
06:45

Design and Application of a Fault Detection Method Based on Adaptive Filters and Rotational Speed Estimation for an Electro-Hydrostatic Actuator

Published on: October 28, 2022

1.8K

Area of Science:

  • Deep Learning
  • Mathematical Foundations
  • Artificial Intelligence

Background:

  • Deep learning relies on the theorem that neural networks can approximate continuous functions.
  • Current methods lack explicit guidance on network architecture and weight determination.
  • Training deep neural networks does not guarantee optimal weight convergence.

Purpose of the Study:

  • To develop an explicit architecture for a universal deep network.
  • To derive an explicit formula for calculating network weights, eliminating the need for training.
  • To address the limitations of current deep learning training methodologies.

Main Methods:

  • Utilizing Gray code ordering to define a universal deep network architecture.
  • Developing a direct formula for calculating network weights based on the target function.
  • Comparing the performance of the proposed deep network with shallow piecewise linear interpolation.

Main Results:

  • An explicit, target function-independent architecture for a universal deep network was developed.
  • An explicit formula for calculating network weights was derived, removing the need for training.
  • The proposed deep network achieves identical results to shallow piecewise linear interpolation for any target function.

Conclusions:

  • The developed deep network architecture and weight calculation formula provide a training-free approach to function approximation.
  • This method overcomes the uncertainty and potential sub-optimality associated with traditional deep learning training.
  • The findings offer a deterministic and efficient alternative for universal function approximation in deep learning.