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

Local model network identification with Gaussian processes.

Gregor Gregorcic1, Gordon Lightbody

  • 1Control and Automation Development Department, Anstalt für Verbrennungskraftmaschinen List, A-8020 Graz, Austria. gregor.gregorcic@avl.com

IEEE Transactions on Neural Networks
|January 29, 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

A Deep Learning Approach to Grading Neonatal Hypoxic-Ischemic Encephalopathy Using ECG Spectrograms<sup></sup>.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Detection of Neurovascular Coupling in Full-Term Neonates Using Wavelet Coherence and Phase-Locking Value.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Analysis of the impact of deep learning know-how and data in modelling neonatal EEG.

Scientific reports·2024
Same author

Predicting low cognitive ability at age 5 years using perinatal data and machine learning.

Pediatric research·2024
Same author

Prediction of 2-Year Cognitive Outcomes in Very Preterm Infants Using Machine Learning Methods.

JAMA network open·2023
Same author

Neonatal EEG graded for severity of background abnormalities in hypoxic-ischaemic encephalopathy.

Scientific data·2023
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 local linear Gaussian process (GP) model network to improve computational efficiency and transparency in model-based control. This approach enhances GP applications by combining local modeling with GP priors for complex systems.

Area of Science:

  • Control Engineering
  • Machine Learning
  • Computational Statistics

Background:

  • Bayesian Gaussian processes (GPs) offer advantages in model-based control, particularly in predicting output variance.
  • However, standard GP models are computationally intensive and lack transparency.
  • Existing methods like neural networks (NNs) and fuzzy models do not fully leverage GP's predictive variance capabilities.

Purpose of the Study:

  • To develop a more computationally efficient and transparent Gaussian process modeling approach for control strategies.
  • To introduce a local linear Gaussian process (LGP) model network that addresses the limitations of traditional GP models.
  • To present a novel algorithm for the structure determination and optimization of local model networks.

Main Methods:

Related Experiment Videos

  • A local linear Gaussian process (LGP) model network is proposed, integrating local model network principles with GP priors.
  • A new algorithm is developed for the structure determination and optimization of these local model networks.
  • The methodology is demonstrated on a nonlinear laboratory-scale process rig.

    • Main Results:

    • The proposed LGP model network significantly reduces computational load compared to standard GP models.
    • Increased transparency in the modeling process is achieved.
    • The novel structure determination algorithm is shown to be widely applicable to local model network training.

    Conclusions:

    • The local linear Gaussian process (LGP) model network provides an effective solution for computationally demanding and opaque GP models in control.
    • The developed methodology enhances the practical applicability of Gaussian processes in complex control systems.
    • The approach offers a promising direction for advancing model-based control strategies through improved efficiency and interpretability.