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

Recursive Bayesian recurrent neural networks for time-series modeling.

Derrick T Mirikitani1, Nikolay Nikolaev

  • 1Department of Computing, Goldsmiths College, University of London, London, UK. D.T.Mirikitani@gold.ac.uk

IEEE Transactions on Neural Networks
|December 31, 2009
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models01:06

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models

Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
Sequence Networks of Rotating Machines01:24

Sequence Networks of Rotating Machines

A Y-connected synchronous generator, grounded through a neutral impedance, is designed to produce balanced internal phase voltages with only positive-sequence components. The generator's sequence networks include a source voltage that is exclusively in the positive-sequence network. The sequence components of line-to-ground voltages at the generator terminals illustrate this configuration.
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...

You might also read

Related Articles

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

Sort by
Same author

Analytical transfer characteristics of axially symmetric 3D optical imaging systems.

Journal of the Optical Society of America. A, Optics, image science, and vision·2026
Same author

A pragmatic methodology for the evaluation of digital care management in the context of multimorbidity.

Journal of medical economics·2021
Same author

A Framework for Predicting Impactability of Digital Care Management Using Machine Learning Methods.

Population health management·2019
Same author

Focus variation microscope: linear theory and surface tilt sensitivity.

Applied optics·2016
Same author

Identification of the psychometric properties of the leadership influence over professional practice environments scale.

The Journal of nursing administration·2013
Same author

Doing more with less: a method for low total mass, affinity measurement using variable-length nanotethers.

Analytical chemistry·2011
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

This study introduces a new probabilistic method for training recurrent neural networks (RNNs), enhancing time-series modeling. The approach offers better generalization and stable performance compared to existing algorithms.

Area of Science:

  • Machine Learning
  • Artificial Intelligence
  • Time-Series Analysis

Background:

  • Recurrent Neural Networks (RNNs) are powerful for sequential data but face challenges in training stability and generalization.
  • Existing training algorithms like Real-Time Recurrent Learning and Extended Kalman Filter have limitations in handling complex time-series dynamics.

Purpose of the Study:

  • To develop a novel probabilistic approach for recursive second-order training of RNNs.
  • To improve the accuracy and stability of RNNs in time-series modeling tasks.
  • To provide a principled method for hyperparameter tuning and regularization.

Main Methods:

  • Derivation of a general recursive Bayesian Levenberg-Marquardt algorithm.
  • Sequential updating of network weights and the Hessian (covariance) matrix.

Related Experiment Videos

  • Adaptation of noise and local weight prior hyperparameters to model data noise and parameter uncertainties.

    • Main Results:

    • The proposed method demonstrates superior performance in time-series modeling compared to standard algorithms.
    • Achieved better generalization capabilities due to principled hyperparameter handling.
    • Exhibited stable numerical performance during training.

    Conclusions:

    • The developed probabilistic recursive training framework significantly enhances RNN performance for time-series modeling.
    • The approach offers a robust and principled alternative to existing training methods.
    • Effective management of hyperparameters leads to improved model generalization and reliability.