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

Constrained least absolute deviation neural networks.

Z Wang1, B S Peterson

  • 1Division of Child Psychiatry, Columbia College of Physicians and Surgeons, New York, NY 10032, USA. zw2105@columbia.edu

IEEE Transactions on Neural Networks
|February 14, 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

Prenatal exposure to polycyclic aromatic hydrocarbons, reduced hippocampal subfield volumes, and word reading.

Developmental cognitive neuroscience·2025
Same author

The role of the hippocampus in working memory and word reading: Novel neural correlates of reading among youth living in the context of economic disadvantage.

Developmental cognitive neuroscience·2025
Same author

Evidence for neuroplastic compensation in the cerebral cortex of persons with depressive illness.

Molecular psychiatry·2017
Same author

Alterations in amygdala-prefrontal circuits in infants exposed to prenatal maternal depression.

Translational psychiatry·2016
Same author

Longitudinal magnetic resonance imaging reveals striatal hypertrophy in a rat model of long-term stimulant treatment.

Translational psychiatry·2016
Same author

Compressed sensing MRI combined with SENSE in partial k-space.

Physics in medicine and biology·2012
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 the constrained least absolute deviation neural network (CLADNN) for robust parameter estimation in constrained problems. The CLADNN ensures global convergence and stability, outperforming previous methods for noisy data.

Area of Science:

  • Computational mathematics
  • Machine learning
  • Signal processing

Background:

  • Least absolute deviation (LAD) estimation offers robustness against outliers and noise.
  • Previous work introduced the LAD neural network (LADNN) for unconstrained problems, demonstrating stability and convergence.
  • Practical applications often involve constrained LAD problems, a generalization of unconstrained ones.

Purpose of the Study:

  • To develop a novel neural network for solving general constrained LAD problems.
  • To establish the theoretical stability and convergence properties of the new network.
  • To evaluate the network's performance in robust parameter estimation for nonlinear curve fitting.

Main Methods:

  • Introduction of the constrained least absolute deviation neural network (CLADNN).

Related Experiment Videos

  • Theoretical analysis using Lyapunov stability to prove global convergence.
  • Numerical simulations for validation on constrained LAD problems and nonlinear curve fitting.

    • Main Results:

    • The CLADNN is proven to be Lyapunov stable and guarantees global convergence to the exact solution, irrespective of initial conditions.
    • Numerical simulations confirm the CLADNN's effectiveness in solving constrained LAD problems.
    • The CLADNN demonstrates robust performance in nonlinear curve fitting applications.

    Conclusions:

    • The CLADNN provides an effective and robust solution for constrained LAD problems.
    • The network's stability and global convergence properties make it reliable for parameter estimation.
    • CLADNN shows significant potential for applications in signal and image processing requiring robust estimation.