Neural networks for solving constrained optimization problems

V.M. Mladenov; J.A. Hegt

Neural networks for solving constrained optimization problems

V.M. Mladenov, J.A. Hegt

Integrated Circuits

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

2567 Downloads (Pure)

Abstract

In this paper we consider several Neural Network architectures for solving constrained optimization problems with inequality constrains. We present a new architecture based on the exact penalty function approach. Simulation results based on SIMULINK® models are given and compared.

Original language	English
Title of host publication	4th WSEAS Multi-Conference on Circuits, Systems, Communications and Computers (CSCC'2000), Vouliagmeni (Athens), Greece, July 10-15, 2000
Pages	1351-1359
Publication status	Published - 2000

Access to Document

586113608007753Final author version , 677 KB

Cite this

@inproceedings{bf1adf9b086d4a58938a4440f27b1135,

title = "Neural networks for solving constrained optimization problems",

abstract = "In this paper we consider several Neural Network architectures for solving constrained optimization problems with inequality constrains. We present a new architecture based on the exact penalty function approach. Simulation results based on SIMULINK{\textregistered} models are given and compared.",

author = "V.M. Mladenov and J.A. Hegt",

year = "2000",

language = "English",

pages = "1351--1359",

booktitle = "4th WSEAS Multi-Conference on Circuits, Systems, Communications and Computers (CSCC'2000), Vouliagmeni (Athens), Greece, July 10-15, 2000",

}

TY - GEN

T1 - Neural networks for solving constrained optimization problems

AU - Mladenov, V.M.

AU - Hegt, J.A.

PY - 2000

Y1 - 2000

N2 - In this paper we consider several Neural Network architectures for solving constrained optimization problems with inequality constrains. We present a new architecture based on the exact penalty function approach. Simulation results based on SIMULINK® models are given and compared.

AB - In this paper we consider several Neural Network architectures for solving constrained optimization problems with inequality constrains. We present a new architecture based on the exact penalty function approach. Simulation results based on SIMULINK® models are given and compared.

M3 - Conference contribution

SP - 1351

EP - 1359

BT - 4th WSEAS Multi-Conference on Circuits, Systems, Communications and Computers (CSCC'2000), Vouliagmeni (Athens), Greece, July 10-15, 2000

ER -

Neural networks for solving constrained optimization problems

Abstract

Access to Document

Fingerprint

Cite this