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

Training trajectories by continuous recurrent multilayer networks.

L Leistritz1, M Galicki, H Witte

  • 1Inst. of Med. Statistics, Comput. Sci. and Documentation, Friedrich-Schiller-Univ., Jena.

IEEE Transactions on Neural Networks
|February 5, 2008
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

<i>Meloidogyne marylandi</i> is Involved in, but not the Primary Cause of Creeping Bentgrass Decline of Putting Greens in Southern California.

Journal of nematology·2024
Same author

Update: The molecular spectrum of virus-associated high-grade B-cell non-Hodgkin lymphomas.

Blood reviews·2024
Same author

Anaesthetic efficacy and postinduction hypotension with remimazolam compared with propofol: a multicentre randomised controlled trial.

Anaesthesia·2024
Same author

[Current status of teaching in lung ultrasound : Query of knowledge, utilization, need, and preferred teaching method].

Medizinische Klinik, Intensivmedizin und Notfallmedizin·2017
Same author

Topographical principles and peculiarities of operative access in lumbar disc extrusion.

Der Orthopade·2017
Same author

[Pre-operative documentation of individual in-patient therapy goals : A medical staff questionnaire].

Der Anaesthesist·2016
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 novel method for training continuous recurrent neural networks using an optimal control framework. The approach effectively trains network trajectories for approximating nonlinear dynamic systems.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Recurrent neural networks (RNNs) are powerful tools for modeling dynamic systems.
  • Training RNNs for complex trajectories, especially nonlinear ones, remains a challenge.
  • Existing methods may struggle with arbitrary accuracy in approximating general nonlinear dynamics.

Purpose of the Study:

  • To develop an efficient training algorithm for continuous recurrent neural networks.
  • To leverage optimal control theory for determining network weights.
  • To enable accurate approximation of general nonlinear dynamic systems.

Main Methods:

  • The study frames the network training problem within an optimal control framework.
  • Weights of the multilayer perceptron feedforward parts are treated as control variables.

Related Experiment Videos

  • A training algorithm based on a variational formulation of Pontryagin's maximum principle is proposed.

    • Main Results:

    • The proposed method transforms the trajectory training problem into an optimal control problem.
    • Continuous recurrent neural networks with multilayer perceptrons can approximate nonlinear systems with high accuracy.
    • Computer simulations demonstrate the effectiveness of the developed training algorithm.

    Conclusions:

    • The optimal control approach provides an efficient method for training continuous recurrent neural networks.
    • This technique enhances the capability of neural networks to model complex nonlinear dynamic systems.
    • The proposed algorithm shows promise for various applications requiring accurate dynamic system approximation.