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

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

107
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
107
Linear Approximation in Time Domain01:21

Linear Approximation in Time Domain

130
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,...
130
Second Order systems II01:18

Second Order systems II

178
In an underdamped second-order system, where the damping ratio ζ is between 0 and 1, a unit-step input results in a transfer function that, when transformed using the inverse Laplace method, reveals the output response. The output exhibits a damped sinusoidal oscillation, and the difference between the input and output is termed the error signal. This error signal also demonstrates damped oscillatory behavior. Eventually, as the system reaches a steady state, the error diminishes to zero.
178
Linear Approximation in Frequency Domain01:26

Linear Approximation in Frequency Domain

143
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....
143
Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model01:13

Parameters Affecting Nonlinear Elimination: Zero-Order Input, First-Order Absorption and Two-Compartment Model

129
Drugs administered through various routes can lead to nonlinear elimination, resulting in complex pharmacokinetic behaviors crucial to understanding efficacious drug dosing.
When a drug is administered through a constant intravenous infusion and eliminated via nonlinear pharmacokinetics, it follows zero-order input. For example, oral drugs undergo first-order absorption upon administration and are eliminated through nonlinear pharmacokinetics.
In the case of subcutaneously administered drugs,...
129
Difference Equation Solution using z-Transform01:24

Difference Equation Solution using z-Transform

389
The z-transform is a powerful tool for analyzing practical discrete-time systems, often represented by linear difference equations. Solving a higher-order difference equation requires knowledge of the input signal and the initial conditions up to one term less than the order of the equation.
The z-transform facilitates handling delayed signals by shifting the signal in the z-domain, which corresponds to delaying the signal in the time domain, and advancing signals by similarly shifting in the...
389

You might also read

Related Articles

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

Sort by
Same author

Computational Modelling of Novelty Detection in the Mismatch Negativity Protocols and Its Impairments in Schizophrenia.

The European journal of neuroscience·2026
Same author

Computational modelling of schizophrenia-associated alterations of ion-channel-encoding gene expression predicts a decrease in delta power.

bioRxiv : the preprint server for biology·2025
Same author

Computational modelling of novelty detection in the mismatch negativity protocols and its impairments in schizophrenia.

bioRxiv : the preprint server for biology·2025
Same author

Modeling neuron-astrocyte interactions in neural networks using distributed simulation.

PLoS computational biology·2025
Same author

The coming decade of digital brain research: A vision for neuroscience at the intersection of technology and computing.

Imaging neuroscience (Cambridge, Mass.)·2025
Same author

Pre- and Post-synaptic Mechanisms of Neuronal Inhibition Assessed Through Biochemically Detailed Modeling of GABA<sub>B</sub> Receptor Signaling.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2025

Related Experiment Video

Updated: Sep 22, 2025

Modeling Fast-scan Cyclic Voltammetry Data from Electrically Stimulated Dopamine Neurotransmission Data Using QNsim1.0
07:41

Modeling Fast-scan Cyclic Voltammetry Data from Electrically Stimulated Dopamine Neurotransmission Data Using QNsim1.0

Published on: June 5, 2017

10.0K

Accelerating Neural ODEs Using Model Order Reduction.

Mikko Lehtimaki, Lassi Paunonen, Marja-Leena Linne

    IEEE Transactions on Neural Networks and Learning Systems
    |May 26, 2022
    PubMed
    Summary
    This summary is machine-generated.

    Mathematical model order reduction (MOR) compresses and accelerates Neural Ordinary Differential Equations (ODEs) by simulating dynamics in low-dimensional subspaces. This approach offers a favorable balance of speed and accuracy for deep learning applications.

    More Related Videos

    Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
    09:44

    Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

    Published on: March 8, 2024

    5.1K
    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

    1.8K

    Related Experiment Videos

    Last Updated: Sep 22, 2025

    Modeling Fast-scan Cyclic Voltammetry Data from Electrically Stimulated Dopamine Neurotransmission Data Using QNsim1.0
    07:41

    Modeling Fast-scan Cyclic Voltammetry Data from Electrically Stimulated Dopamine Neurotransmission Data Using QNsim1.0

    Published on: June 5, 2017

    10.0K
    Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
    09:44

    Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

    Published on: March 8, 2024

    5.1K
    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

    1.8K

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Dynamical Systems

    Background:

    • Neural Ordinary Differential Equations (ODEs) embed nonlinear dynamical systems into deep learning (DL) models, offering memory efficiency and natural time-series processing.
    • Current Neural ODEs face limitations in practical application due to computationally demanding inference times from numerical solvers.

    Purpose of the Study:

    • To investigate the use of mathematical model order reduction (MOR) techniques for compressing and accelerating Neural ODEs.
    • To develop and validate a novel compression method for Neural ODEs using MOR.

    Main Methods:

    • Implemented MOR by integrating subspace-projection and interpolation operations as neural network layers within Neural ODEs.
    • Compared the MOR-based compression method against neuron pruning and singular value decomposition (SVD)-based weight truncation.
    • Evaluated methods based on the trade-off between acceleration and accuracy in image and time-series classification tasks.

    Main Results:

    • The MOR integration achieved a favorable balance of acceleration and accuracy when compressing convolutional Neural ODEs.
    • SVD-based weight truncation demonstrated good performance in compressing recurrent Neural ODEs.
    • The study successfully demonstrated the efficacy of MOR for enhancing Neural ODE efficiency.

    Conclusions:

    • Integrating MOR with Neural ODEs facilitates efficient, dynamical system-driven deep learning.
    • This approach is particularly beneficial for resource-constrained applications requiring fast inference.
    • MOR presents a viable strategy for overcoming the computational bottlenecks in Neural ODEs.