IMPROVED NEURAL NETWORKS FOR LINEAR AND NONLINEAR PROGRAMMING-Reference-Cited by-同舟云学术

IMPROVED NEURAL NETWORKS FOR LINEAR AND NONLINEAR PROGRAMMING

Published:1991-01 Issue:04 Volume:02 Page:331-339
ISSN:0129-0657
Container-title:International Journal of Neural Systems
language:en
Short-container-title:Int. J. Neur. Syst.

Author:

Chen Jiahan¹,Shanblatt Michael A.¹,Maa Chia-Yiu²

Affiliation:

1. Department of Electrical Engineering, Michigan State University, East Lansing, MI 48824, USA

2. Research and Development Department, Electronic Data Systems, Inc., Auburn Hills, MI 48326, USA

Abstract

A method for improving the performance of artificial neural networks for linear and nonlinear programming is presented. By analyzing the behavior of the conventional penalty function, the reason for the inherent degenerating accuracy is discovered. Based on this, a new combination penalty function is proposed which can ensure that the equilibrium point is acceptably close to the optimal point. A known neural network model has been modified by using the new penalty function and the corresponding circuit scheme is given. Simulation results show that the relative error for linear and nonlinear programming is substantially reduced by the new method.

Publisher

World Scientific Pub Co Pte Lt

Subject

Computer Networks and Communications,General Medicine

Link

https://www.worldscientific.com/doi/pdf/10.1142/S0129065791000303

Cited by 4 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Neural network learning for analog VLSI implementations of support vector machines: a survey;Neurocomputing;2003-09

2. Circuital implementation of support vector machines;Electronics Letters;1998

3. A new neural network for solving linear programming problems;European Journal of Operational Research;1996-09

4. Adaptive control optimization in end milling using neural networks;International Journal of Machine Tools and Manufacture;1995-04