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

Convolution: Math, Graphics, and Discrete Signals01:24

Convolution: Math, Graphics, and Discrete Signals

In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
Convolution Properties I01:20

Convolution Properties I

Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
Convolution Properties II01:17

Convolution Properties II

The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
Neural Circuits01:25

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Deconvolution01:20

Deconvolution

Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Reconstruction of Signal using Interpolation01:10

Reconstruction of Signal using Interpolation

Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next sampling...

You might also read

Related Articles

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

Sort by
Same author

The diagnostic potential of elastosonography in cesarean scar pregnancy.

European journal of obstetrics & gynecology and reproductive biology: X·2025
Same author

The curriculum: The heart and soul of a medical school.

Medical teacher·2024
Same author

Neural ordinary differential equations with irregular and noisy data.

Royal Society open science·2023
Same author

Twice weekly polymerase chain reaction (PCR) surveillance swabs are not as effective as daily antigen testing for containment of severe acute respiratory coronavirus virus 2 (SARS-CoV-2) outbreaks: A modeling study based on real world data from a child and adolescent psychiatry clinic.

Infection control and hospital epidemiology·2023
Same author

Evaluation of Heavy Metal (Lead, Mercury, Cadmium, and Manganese) Levels in Blood, Plasma, and Urine of Adolescents With Aggressive Behavior.

Cureus·2023
Same author

Retrospective Evaluation of Patients With Scorpion Stings Admitted to the Pediatric Emergency Clinic.

Cureus·2022

Related Experiment Videos

Symplectic convolutional neural networks.

Süleyman Yıldız1, Konrad Janik1, Peter Benner2

  • 1Max Planck Institute for Dynamics of Complex Technical Systems, 39106, Magdeburg, Germany.

Neural Networks : the Official Journal of the International Neural Network Society
|June 5, 2026
PubMed
Summary
This summary is machine-generated.

We introduce a novel symplectic convolutional neural network (CNN) for solving differential equations. This new architecture outperforms existing methods, offering a more effective approach for complex physics problems.

Keywords:
AutoencodersConvolutional neural networksHamiltonian systemsNeural networksSymplectic integrators

Related Experiment Videos

Area of Science:

  • Computational Physics
  • Machine Learning
  • Numerical Analysis

Background:

  • Deep learning models, particularly convolutional neural networks (CNNs), are increasingly used for solving complex scientific problems.
  • Traditional CNNs lack inherent structures to preserve physical laws, such as symplecticity, crucial for Hamiltonian systems.
  • Symplectic methods are essential for long-term accurate simulations of conservative systems.

Purpose of the Study:

  • To develop a novel symplectic convolutional neural network (CNN) architecture.
  • To ensure the preservation of symplecticity within the CNN layers for accurate physical simulations.
  • To evaluate the performance of the proposed symplectic CNN against existing methods.

Main Methods:

  • Introduction of a mathematically equivalent form of the convolution layer.
  • Parameterization of CNN layers using symplectic neural networks to maintain symplecticity.
  • Development of a symplectic pooling layer to create a complete symplectic autoencoder.
  • Testing the architecture on the wave, nonlinear Schrödinger (NLS), and sine-Gordon equations.

Main Results:

  • The proposed symplectic CNN architecture successfully preserves symplecticity.
  • Numerical results demonstrate the effectiveness of the symplectic CNN on benchmark differential equations.
  • The symplectic CNN significantly outperforms the linear symplectic autoencoder derived from proper symplectic decomposition.

Conclusions:

  • The developed symplectic CNN provides a robust framework for physics-informed machine learning.
  • This architecture offers improved accuracy and stability for simulating dynamical systems governed by Hamiltonian mechanics.
  • The symplectic CNN represents a significant advancement in applying deep learning to solve complex scientific challenges.