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

Cumulant-based parameter estimation using structured networks.

L X Wang1, J M Mendel

  • 1Dept. of Electr. Eng.-Syst., Univ. of Southern California, Los Angeles, CA.

IEEE Transactions on Neural Networks
|January 1, 1991
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

[Research progress on the rapid reversal of atherosclerotic plaques by macrophage-targeted sonodynamic therapy].

Zhonghua xin xue guan bing za zhi·2026
Same author

[Analysis of the neurodevelopmental impairments and its influencing factors in twins with birth weight discordance before 7 years of age].

Zhonghua er ke za zhi = Chinese journal of pediatrics·2026
Same author

[Sequential treatment for complex tooth trauma of permanent anterior teeth: a case report].

Zhonghua kou qiang yi xue za zhi = Zhonghua kouqiang yixue zazhi = Chinese journal of stomatology·2026
Same author

[Efficacy and safety of venetoclax-cytarabine-homoharringtonine-based cytoreductive therapy before allogeneic hematopoietic stem cell transplantation in refractory/relapsed acute myeloid leukemia with RUNX1::RUNX1T1: a retrospective study].

Zhonghua xue ye xue za zhi = Zhonghua xueyexue zazhi·2026
Same author

[Challenges and strategies in managing distal aneurysms after endovascular repair of aortic dissection].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2026
Same author

[Strategies for aortic arch branch reconstruction during thoracic endovascular aortic repair].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2026
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

A novel structured network estimates moving-average model parameters using cumulant matching. This method utilizes a feedforward network with memory units to learn statistical patterns for accurate parameter estimation.

Area of Science:

  • Signal Processing
  • Machine Learning
  • Statistical Modeling

Background:

  • Moving-average (MA) models are fundamental in time series analysis.
  • Estimating MA model parameters accurately is crucial for various applications.
  • Cumulant matching offers a robust approach for parameter estimation.

Purpose of the Study:

  • To develop a novel structured network for estimating moving-average model parameters.
  • To leverage second-order and third-order cumulant matching for parameter estimation.
  • To provide a network with interpretable weights representing MA parameters.

Main Methods:

  • A two-level, three-layer structured feedforward network is proposed.
  • The network employs random access memory units to control summer connectivities.

Related Experiment Videos

  • A steepest-descent algorithm is used for training the network to learn cumulant patterns.

    • Main Results:

    • The structured network's weights directly correspond to the moving-average parameters.
    • Network outputs match desired second-order or third-order statistics when weights are accurate.
    • Simulations demonstrate the effectiveness of the proposed estimation method.

    Conclusions:

    • The developed structured network provides an effective method for estimating moving-average model parameters.
    • The network's architecture offers physical interpretability of estimated parameters.
    • The cumulant matching approach combined with the structured network shows promise for advanced signal processing tasks.