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

The ensemble approach to neural-network learning and generalization.

B Igelnik1, Y H Pao, S R LeClair

  • 1Case Western Reserve University, Cleveland, OH 44106, USA.

IEEE Transactions on Neural Networks
|February 7, 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 case of mucopolysaccharidosis type ⅢA with ventricular hypertrophy as the first clinical presentation].

Zhonghua xin xue guan bing za zhi·2025
Same author

[Mechanisms by which Mettl3 regulates pericyte-myofibroblast transdifferentiation through PI3K/AKT signaling pathway].

Zhonghua xin xue guan bing za zhi·2024
Same author

[Expression and protective effect of chemerin in idiopathic pulmonary fibrosis].

Zhonghua jie he he hu xi za zhi = Zhonghua jiehe he huxi zazhi = Chinese journal of tuberculosis and respiratory diseases·2023
Same author

[Advancement in endovascular therapy of aortoiliac occlusive disease].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2022
Same author

[Establishment of a cytokine release syndrome associated with chimeric antigen receptor T cell treatment in SCID/Beige mice model].

Zhonghua zhong liu za zhi [Chinese journal of oncology]·2021
Same author

[Drug-coated balloons versus bare metal stent for treatment of femoropopliteal lesions:36 month follow-up results of single center].

Zhonghua wai ke za zhi [Chinese journal of surgery]·2021
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 method enhances learning and generalization in feedforward neural networks using adaptive optimization and linear regression. This approach efficiently determines network parameters and node count for diverse applications.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • General one-hidden layer feedforward neural networks require efficient learning and generalization methods.
  • Existing techniques may lack computational efficiency or adaptability.

Purpose of the Study:

  • To introduce a new, computationally efficient method for learning and generalization in feedforward neural networks.
  • To enable adaptive optimization of network parameters and selection of an appropriate number of nodes.

Main Methods:

  • Utilizes a linear combination of heterogeneous nodes with random parameters.
  • Employs adaptive stochastic optimization for parameter learning using generalization data.
  • Applies linear regression for learning linear coefficients using training data, processing one node at a time.

Related Experiment Videos

Main Results:

  • The method allows for determining the optimal number of network nodes.
  • Demonstrates computational efficiency in learning and generalization.
  • Successfully tested on both mathematical problems and real-world materials science applications.

Conclusions:

  • The proposed method offers an effective and efficient approach for training feedforward neural networks.
  • It provides flexibility in network design and parameter optimization.
  • Shows promise for applications in diverse scientific and technological fields.