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

N-tuple Regression Network.

Nigel M. Allinson1, Aleksander Kolcz

  • 1University of York, York YO1 5DD, UK

Neural Networks : the Official Journal of the International Neural Network Society
|July 1, 1996
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

Basis function models of the CMAC network.

Neural networks : the official journal of the International Neural Network Society·2003
Same journal

Anchor-based disentanglement framework for incremental multi-view clustering.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Complex-valued amplitude-phase interference modeling for adversarially robust classification.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

TraNce: Type-aware hypergraph neural network with biological mediators for drug repositioning.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Decentralized ADMM for factorization-based Low-rank matrix estimation.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Memristive neuromorphic circuit design inspired by the neural mechanisms of conditioned fear.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Q-learning based asynchronous Boolean control networks stabilization with data loss.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

N-tuple neural networks (NTNNs) are modified for non-parametric kernel regression. This approach offers fast, statistically consistent learning independent of training data size, ensuring reliable performance.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Computational Statistics

Background:

  • N-tuple neural networks (NTNNs) are effective for pattern recognition and function approximation.
  • NTNNs possess advantages such as a single-layer structure, non-linear mapping capabilities, and operational simplicity.

Purpose of the Study:

  • To modify the basic NTNN architecture to function as a non-parametric kernel regression estimator.
  • To leverage NTNNs for approximating complex probability density functions (pdfs) and arbitrary function mappings.

Main Methods:

  • A modified NTNN architecture is presented, enabling it to perform non-parametric kernel regression.
  • The network implicitly stores training data, avoiding explicit storage and maintaining constant operation speed.

Related Experiment Videos

Main Results:

  • The modified NTNN demonstrates inherent capability for approximating complex probability density functions (pdfs).
  • The regression network features a statistically consistent, one-pass training procedure.
  • Operation speed remains constant and independent of training set size, ensuring practical implementation performance.

Conclusions:

  • The modified NTNN architecture effectively serves as a non-parametric kernel regression estimator.
  • Implicit data storage in NTNNs guarantees constant operation speed, crucial for practical applications.
  • This approach offers a robust and efficient method for regression tasks with complex data.