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

Dynamical recurrent neural networks--towards environmental time series prediction

A Aussem1, F Murtagh, M Sarazin

  • 1Very Large Telescope Division, European Southern Observatory, Garching bei München, Germany.

International Journal of Neural Systems
|June 1, 1995
PubMed
Summary

Dynamical Recurrent Neural Networks (DRNN) offer history-sensitive forecasts for time series by approximating underlying laws with nonlinear difference equations. This study demonstrates DRNN

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

Diagnosis of Alzheimer's disease: Recommendations from the French Federation of Memory Clinics.

Revue neurologique·2025
Same author

[

European journal of nuclear medicine and molecular imaging·2023
Same author

Managing uncertain recovery for patients nearing the end of life in hospital: a mixed-methods feasibility cluster randomised controlled trial of the AMBER care bundle.

Trials·2019
Same author

Combined assessment of DYRK1A, BDNF and homocysteine levels as diagnostic marker for Alzheimer's disease.

Translational psychiatry·2017
Same author

[Reconciliating neurology and psychiatry: The prototypical case of frontotemporal dementia].

L'Encephale·2016
Same author

The economic burden of urinary tract infections in women visiting general practices in France: a cross-sectional survey.

BMC health services research·2016

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Time Series Analysis

Background:

  • Dynamical Recurrent Neural Networks (DRNN) model synapses as autoregressive filters.
  • DRNNs approximate time series laws using nonlinear difference equations, enabling history-sensitive forecasts without external memory.
  • The training method is temporal-recurrent-backpropagation, efficient due to exponential gradient decay.

Purpose of the Study:

  • To assess the predictive ability of DRNN models for meteorological and astronomical time series.
  • To enable preset telescope instrumental modes hours in advance using reliable environmental forecasts.
  • To compare DRNN performance against traditional methods for complex time series prediction.

Main Methods:

  • DRNN model applied to meteorological and astronomical time series.

Related Experiment Videos

  • Comparison with nonlinear Autoregressive (AR) and Autoregressive Moving Average (ARMA) models using feedforward networks.
  • Fuzzy coding and fuzzy correspondence analysis for astronomical seeing prediction.
  • Nonlinear multiple regression (nowcasting) on fuzzily coded seeing records.

    • Main Results:

    • DRNNs provide history-sensitive forecasts by approximating time series dynamics.
    • The DRNN model demonstrated superior performance in predicting astronomical seeing compared to the fuzzy k-nearest neighbors method.
    • Efficiency of temporal-recurrent-backpropagation is enhanced by exponential decay of backpropagated gradients.

    Conclusions:

    • DRNNs are effective for time series forecasting, particularly for complex and erratic data like astronomical seeing.
    • The model's ability to learn internal dynamics allows for accurate predictions without explicit external memory.
    • DRNNs show promise for applications requiring reliable environmental forecasts, such as optimizing astronomical telescope operations.