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

Ridge polynomial networks.

Y Shin1, J Ghosh

  • 1Dept. of Electr. and Comput. Eng., Texas Univ., Austin, TX.

IEEE Transactions on Neural Networks
|January 1, 1995
PubMed
Summary
This summary is machine-generated.

This study introduces the ridge polynomial network (RPN), a novel connectionist model capable of approximating any continuous function with high accuracy. The RPN offers an efficient architecture for machine learning tasks.

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

Isolation, characterization and evaluation of growth kinetics and multilineage differentiation of ovine ovarian mesenchymal stem cells.

Theriogenology·2026
Same author

First results from testing of the full ITER hard x-ray monitor prototype on the ADITYA Upgrade tokamak.

The Review of scientific instruments·2026
Same author

Capivasertib plus paclitaxel as first-line treatment for metastatic triple-negative breast cancer: results from the randomised, global phase III CAPItello-290 trial.

Annals of oncology : official journal of the European Society for Medical Oncology·2025
Same author

Enhancing marine magnetic anomaly interpretation with anisotropic diffusion and deep transfer learning.

Scientific reports·2025
Same author

Upgraded space and time resolved visible spectroscopic diagnostic on ADITYA-U tokamak.

The Review of scientific instruments·2024
Same author

Author Correction: Role of pinch in Argon impurity transport in ohmic discharges of Aditya-U Tokamak.

Scientific reports·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

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Neural Networks

Background:

  • Higher-order feedforward networks possess fast learning properties but can lack efficiency and regularity.
  • Approximation capabilities of neural networks are crucial for solving complex mathematical and data-driven problems.

Purpose of the Study:

  • To introduce and analyze the ridge polynomial network (RPN), a novel polynomial connectionist network.
  • To demonstrate the RPN's ability to uniformly approximate any continuous function in a multidimensional space with arbitrary accuracy.
  • To highlight the RPN's advantages in efficiency and architectural regularity over existing models.

Main Methods:

  • The study presents the ridge polynomial network (RPN) as a generalization of the pi-sigma network, utilizing a specific form of ridge polynomials.

Related Experiment Videos

  • Theoretical analysis demonstrates that any multivariate polynomial can be represented and realized by an RPN, leveraging the Weierstrass polynomial approximation theorem.
  • A constructive learning algorithm is developed and applied for RPN training.

    • Main Results:

    • The RPN exhibits uniform approximation capabilities for continuous functions on compact sets in R(d) with arbitrary accuracy.
    • The RPN offers a more efficient and regular architecture compared to traditional higher-order feedforward networks, while retaining fast learning.
    • Simulation results confirm the RPN's effectiveness in surface fitting, high-dimensional data classification, and multivariate polynomial function realization.
    • The developed learning algorithm leads to smooth generalization and steady learning performance.

    Conclusions:

    • The ridge polynomial network (RPN) is a powerful tool for function approximation and machine learning.
    • The RPN's architecture and learning algorithm provide a robust and efficient solution for complex approximation tasks.
    • The RPN facilitates incremental network growth, offering flexibility in model development.