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 Experiment Videos

A recurrent neural network for modelling dynamical systems.

C A Bailer-Jones1, D J MacKay, P J Withers

  • 1Cavendish Laboratory, University of Cambridge, UK. calj@mpia-hd.mpg.de

Network (Bristol, England)
|April 30, 1999
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Pvf1-Pvr-mediated crosstalk between trachea and gut guides intestinal stem cell migration to promote gut regeneration.

Nature communications·2025
Same author

Exploration of fs-laser ablation parameter space for 2D/3D imaging of soft and hard materials by tri-beam microscopy.

Ultramicroscopy·2023
Same author

Why Is It So Challenging to Measure Residual Stresses ?

Experimental mechanics·2022
Same author

Core Imaging Library - Part I: a versatile Python framework for tomographic imaging.

Philosophical transactions. Series A, Mathematical, physical, and engineering sciences·2021
Same author

Correction of artefacts associated with large area EBSD.

Ultramicroscopy·2021
Same author

Macro-, meso- and microstructural characterization of metallic lattice structures manufactured by additive manufacturing assisted investment casting.

Scientific reports·2021
Same journal

Enhancing IoT security: A Creative Swagger Optimization algorithm for DDoS defence.

Network (Bristol, England)·2026
Same journal

Parametric optimization for electrical discharge diamond grinding (EDDG) system using dual approach.

Network (Bristol, England)·2025
Same journal

A novel lung cancer diagnosis model using hybrid convolution (2D/3D)-based adaptive DenseUnet with attention mechanism.

Network (Bristol, England)·2025
Same journal

Hybrid optimization enabled Eff-FDMNet for Parkinson's disease detection and classification in federated learning.

Network (Bristol, England)·2025
Same journal

AI-driven plant disease detection with tailored convolutional neural network.

Network (Bristol, England)·2025
Same journal

Layer modified residual Unet++ for speech enhancement using Aquila Black widow optimizer algorithm.

Network (Bristol, England)·2025
See all related articles

This study presents a new recurrent network for modeling dynamical systems from sparse, discrete data. The model effectively predicts future states and infers hidden variables, showing promise for applications like metal forging.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Dynamical Systems Modeling

Background:

  • Real-world processes often yield discrete-time measurements of external and state variables.
  • Modeling these systems is challenging due to non-uniform sampling and varying timescales.
  • Existing models struggle with sparse or incomplete data.

Purpose of the Study:

  • To introduce a novel recurrent network architecture for modeling general dynamical systems.
  • To enable learning from multiple temporal patterns with non-uniform sampling.
  • To address the challenge of sparse training data in system identification.

Main Methods:

  • Development of a recurrent network architecture tailored for discrete-time dynamical systems.
  • Training the network on temporal patterns with varying timescales and sampling intervals.

Related Experiment Videos

  • Demonstration on a synthetic problem with data available only at the final time step.

    • Main Results:

    • The network accurately predicts final time-step states for unseen temporal processes.
    • It successfully reproduces the sequence of state variables at earlier time points.
    • The model infers the existence and role of unobserved state variables.

    Conclusions:

    • The proposed recurrent network effectively models dynamical systems using sparse, discrete data.
    • Its ability to handle non-uniform sampling and infer hidden states is a significant advancement.
    • This approach holds potential for applications in fields like metal forging modeling.