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

Trajectory generation and modulation using dynamic neural networks.

P Zegers1, M K Sundareshan

  • 1Fac. de Ingenieria, Univ. de los Andes, Santiago, Chile.

IEEE Transactions on Neural Networks
|February 2, 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

Dry eye is matched by increased intrasubject variability in tear osmolarity as confirmed by machine learning approach.

Archivos de la Sociedad Espanola de Oftalmologia·2019
Same author

Supervised training of dynamical neural networks for associative memory design and identification of nonlinear maps.

International journal of neural systems·1994
Same author

Adaptive image contrast enhancement based on human visual properties.

IEEE transactions on medical imaging·1994
Same author

Identification and decentralized adaptive control using dynamical neural networks with application to robotic manipulators.

IEEE transactions on neural networks·1993
Same author

Equilibrium characterization of dynamical neural networks and a systematic synthesis procedure for associative memories.

IEEE transactions on neural networks·1991
Same author

On the equivalence of mathematical models for cell proliferation kinetics.

Cell and tissue kinetics·1984
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 presents a dynamic neural network (DNN) for trajectory generation. The novel hybrid recurrent neural network (RNN) and nonrecurrent neural network (NRNN) architecture effectively emulates complex spatio-temporal patterns.

Area of Science:

  • Computational Neuroscience
  • Machine Learning
  • Control Systems

Background:

  • Trajectory generation using neural networks presents a significant spatio-temporal learning challenge.
  • Existing methods may struggle with emulating complex patterns independently of initial conditions.

Purpose of the Study:

  • To introduce a novel dynamic system for generating desired trajectory behavior.
  • To design a system capable of emulating prespecified spatio-temporal patterns irrespective of initial conditions.

Main Methods:

  • Development of a dynamic neural network (DNN), a hybrid architecture combining a recurrent neural network (RNN) and a nonrecurrent neural network (NRNN).
  • The RNN generates a limit cycle, which the NRNN reshapes into the target trajectory.
  • A systematic synthesis procedure based on relay control systems is used to configure the RNN.

Related Experiment Videos

Main Results:

  • The proposed DNN architecture is demonstrated to be simple to train.
  • The cascade arrangement of RNN and NRNN can emulate complex trajectory behaviors.
  • An effective solution for online trajectory modulation using external inputs is presented.

Conclusions:

  • The dynamic neural network (DNN) offers a powerful and flexible approach to trajectory generation.
  • The hybrid RNN-NRNN architecture successfully addresses spatio-temporal learning challenges.
  • The system demonstrates robust performance in both trajectory generation and modulation tasks.