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

A high-performance feedback neural network for solving convex nonlinear programming problems.

Yee Leung1, Kai-Zhou Chen, Xing-Bao Gao

  • 1Dept. of Geogr. and Resource Manage., Chinese Univ. of Hong Kong, China.

IEEE Transactions on Neural Networks
|February 5, 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

Clinicopathologic and molecular predictors of survival in BRCA-deficient tubo-ovarian high-grade serous carcinoma.

Nature communications·2026
Same author

Beyond BRCA deficiency: Clinical and molecular predictors of survival in patients with BRCA-deficient tubo-ovarian high-grade serous carcinoma.

Research square·2025
Same author

Beyond <i>BRCA</i> deficiency: Clinical and molecular predictors of survival in patients with <i>BRCA</i>-deficient tubo-ovarian high-grade serous carcinoma.

medRxiv : the preprint server for health sciences·2025
Same author

Routine Tumor Testing for Homologous Recombination Deficiency in Patients With High Grade Epithelial Ovarian Cancer at a Statewide Gynecological Cancer Service in Western Australia: An Observational Study.

Cancer reports (Hoboken, N.J.)·2025
Same author

Cervical screening approach of self-collection, point-of-care HPV testing, and same-day colposcopy among Aboriginal and Torres Strait Islander women in remote Western Australia (the PREVENT Project): an implementation study.

The Lancet. Public health·2025
Same author

A Single Arm Pilot Observational Study to Evaluate the Safety and Feasibility of a Pre-Operative Very Low Calorie Diet in Severely Obese Patients With Endometrial Cancer.

Cancer reports (Hoboken, N.J.)·2025
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 novel feedback neural network for convex nonlinear programming. The model offers high performance, simplicity, and improved stability, solving various optimization problems efficiently.

Area of Science:

  • Computational Mathematics
  • Artificial Intelligence
  • Optimization Theory

Background:

  • Traditional neural network models for optimization often involve complex components like dual variables and Lagrange multipliers.
  • Existing models may lack simplicity in structure and robustness in terms of stability.
  • Solving convex nonlinear programming problems efficiently and reliably remains a significant challenge in computational science.

Purpose of the Study:

  • To propose a high-performance feedback neural network model for convex nonlinear programming problems.
  • To develop a model that avoids complex elements such as dual variables, penalty parameters, and Lagrange multipliers.
  • To enhance the structural simplicity and asymptotic stability of neural network optimization models.

Main Methods:

Related Experiment Videos

  • A novel approach based on successive approximation is employed to design the feedback neural network.
  • The network is structured with a minimal number of state variables, simplifying its architecture.
  • Theoretical analysis is conducted to demonstrate the asymptotic stability of the proposed network.

Main Results:

  • The proposed feedback neural network effectively solves convex nonlinear programming problems.
  • The network demonstrates superior asymptotic stability, converging to optimal solutions from any initial point.
  • The model successfully handles linear programming and convex quadratic programming problems, showcasing versatility.

Conclusions:

  • The new feedback neural network model provides a high-performance, stable, and structurally simple solution for convex nonlinear programming.
  • The model's ability to solve a range of optimization problems and its potential applicability to other optimization tasks highlight its significance.
  • Simulation examples validate the feasibility and efficiency of the proposed approach.