Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

A recurrent neural network for solving nonlinear convex programs subject to linear constraints.

Youshen Xia¹, Jun Wang

¹Department of Applied Mathematics, Nanjing University of Posts and Telecommunications, Nanjing 210003, China. ysxia2001@yahoo.com

IEEE Transactions on Neural Networks

|March 25, 2005

Summary

We introduce a novel recurrent neural network for solving nonlinear convex programming problems. This new approach offers a simpler structure and faster convergence without needing strict Lipschitz continuity.

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

Synthesis and micellization of amphiphilic brush-coil block copolymer based on poly(epsilon-caprolactone) and PEGylated polyphosphoester.

Biomacromolecules·2006

Same author

Intravenous transplantation of mesenchymal stem cells improves cardiac performance after acute myocardial ischemia in female rats.

Transplant international : official journal of the European Society for Organ Transplantation·2006

Same author

[Effects of mechanical tensile stress on the expression of ICAM-1 mRNA in osteoblasts differentiated from rBMSCs].

Sichuan da xue xue bao. Yi xue ban = Journal of Sichuan University. Medical science edition·2006

Same author

[Effects of osteoporosis on experimental tooth movement in aged rats].

Sichuan da xue xue bao. Yi xue ban = Journal of Sichuan University. Medical science edition·2006

Same author

MCALIGN2: faster, accurate global pairwise alignment of non-coding DNA sequences based on explicit models of indel evolution.

BMC bioinformatics·2006

Same author

[Managements of masked mastoiditis].

Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery·2006

Area of Science:

Optimization
Machine Learning
Applied Mathematics

Background:

Nonlinear convex programming problems with linear constraints are common in various fields.
Existing neural network approaches often have complex structures and limitations.

Purpose of the Study:

To propose a new recurrent neural network (RNN) for solving nonlinear convex programming problems.
To demonstrate a simpler and more efficient neural network solution compared to existing methods.

Main Methods:

Development of a novel recurrent neural network architecture.
Analysis of Lyapunov stability and global convergence properties.
Testing with numerical examples to showcase applicability.

Main Results:

Related Experiment Videos

The proposed RNN exhibits Lyapunov stability and finite-time global convergence to optimal solutions.
The network achieves convergence under strict convexity without requiring Lipschitz continuity of the objective function.
The network demonstrates a simpler structure and lower implementation complexity.

Conclusions:

The proposed recurrent neural network is a viable and efficient tool for solving nonlinear convex programming problems.
This method offers advantages over existing approaches by relaxing convergence conditions and simplifying implementation.