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

285
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,...
285
Linear Approximation in Frequency Domain01:26

Linear Approximation in Frequency Domain

313
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....
313
Quadratic Models01:23

Quadratic Models

127
Quadratic models are mathematical representations used to describe relationships in which the rate of change changes at a constant rate. These models appear in a wide variety of natural and engineered systems, especially those involving motion, forces, and optimization. One common application is analyzing the vertical motion of objects influenced by gravity, such as a ball thrown into the air.In such scenarios, the object's height changes over time in a curved pattern, rising to a maximum point...
127
Accuracy, limits, and approximation01:28

Accuracy, limits, and approximation

1.0K
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...
1.0K
Quadratic Equations01:29

Quadratic Equations

194
A quadratic equation is an algebraic expression where a variable is raised to the second power and combined with its first power and a constant; all equated to zero. These equations are frequently used to model relationships involving area, motion, and optimization. The general representation of a quadratic equation iswhere a, b, and c are real values, and a is nonzero to ensure the presence of the squared term.One method for solving a quadratic equation involves rewriting it as a product of...
194
Improving Translational Accuracy02:07

Improving Translational Accuracy

13.9K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
13.9K

You might also read

Related Articles

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

Sort by
Same author

Boosting Geometric Invariants for Discriminative Forensics of Large-Scale Generated Visual Content.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Societyยท2025
Same author

SMART: Self-Supervised Learning for Metal Artifact Reduction in Computed Tomography Using Range Null Space Decomposition.

IEEE transactions on medical imagingยท2025
Same author

Federated Metadata-Constrained iRadonMAP Framework with Mutual Learning for All-in-One Computed Tomography Imaging.

Cyborg and bionic systems (Washington, D.C.)ยท2025
Same author

UniAda: Domain Unifying and Adapting Network for Generalizable Medical Image Segmentation.

IEEE transactions on medical imagingยท2025
Same author

Solving Zero-Shot Sparse-View CT Reconstruction With Variational Score Solver.

IEEE transactions on medical imagingยท2024
Same author

Spatial distribution of rare earth elements and their impact factors in an area with a high abundance of regolith-hosted deposits.

Chemosphereยท2024
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Societyยท2026
Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Societyยท2026
Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Societyยท2026
Same journal

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

Neural networks : the official journal of the International Neural Network Societyยท2026
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Societyยท2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Societyยท2026
See all related articles

Related Experiment Video

Updated: Dec 28, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Universal approximation with quadratic deep networks.

Fenglei Fan1, Jinjun Xiong2, Ge Wang1

  • 1Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY, 12180, USA.

Neural Networks : the Official Journal of the International Neural Network Society
|February 17, 2020
PubMed
Summary
This summary is machine-generated.

Deep quadratic neural networks, using quadratic neurons instead of conventional ones, offer enhanced expressive power and efficiency. This study proves their superior capabilities in function approximation and network architecture.

Keywords:
Approximation theoryDeep learningQuadratic networks

Related Experiment Videos

Last Updated: Dec 28, 2025

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Deep Learning

Background:

  • Deep learning models have seen significant advancements in various applications.
  • Previous research introduced quadratic neurons and deep quadratic neural networks, enhancing expressive capability.
  • The comparative advantage of deep quadratic networks over conventional networks remains under-explored.

Purpose of the Study:

  • To investigate the enhanced expressive capability of deep quadratic networks compared to conventional neural networks.
  • To address four key questions regarding function approximation efficiency, unique expression capabilities, universal approximation insights, and network compactness.
  • To theoretically demonstrate the benefits of quadratic neurons in deep learning architectures.

Main Methods:

  • The study proposes four interconnected theorems to analyze deep quadratic networks.
  • Theoretical analysis is employed to compare the performance of quadratic and conventional neurons.
  • The research focuses on function approximation capabilities and network properties like weight count and computational capacity.

Main Results:

  • Quadratic networks can approximate certain functions significantly more efficiently than conventional networks.
  • Deep quadratic networks possess the capability to express functions not representable by conventional neurons within the same structure.
  • The study provides new insights into universal approximation theorems.
  • Quantized quadratic networks can achieve the same approximation accuracy with fewer weights than quantized conventional networks.

Conclusions:

  • Deep quadratic networks offer superior expressive efficiency and unique capabilities compared to conventional networks.
  • Quadratic neurons enable more compact network architectures and potentially greater computational capacity.
  • The findings highlight the potential of quadratic neurons to advance deep learning theory and applications.