Neural networks for nonlinear programming

Kennedy, Michael Peter; Chua, Leon O.

doi:10.1109/31.1783

Cited by 1,030 publications

(374 citation statements)

References 15 publications

Supporting

Mentioning

360

Contrasting

Unclassified

Order By: Relevance

“…In Theorem 1 and Corollary 1, we do not need the assumptions of boundedness, monotonicity, and differentiability for the activation functions, moreover, the model discussed is with time-varying delays. Clearly, the proposed results are different from those in [2,5,6,8,12,13,14,15] and the references cited therein. Therefore, the results of this paper are new and they complement previously known results.…”

Section: Corollary 1 the Equilibrium Point Of Eq(1) Is Globally Asycontrasting

confidence: 72%

Global Stability Analysis for a Class of Cohen-Grossberg Neural Network Models

Guo¹

2012

Bulletin of the Korean Mathematical Society

View full text Add to dashboard Cite

show abstract

Section: Corollary 1 the Equilibrium Point Of Eq(1) Is Globally Asycontrasting

confidence: 72%

Global Stability Analysis for a Class of Cohen-Grossberg Neural Network Models

Guo¹

2012

Bulletin of the Korean Mathematical Society

View full text Add to dashboard Cite

show abstract

“…BP neural network includes input layer, hidden layer and output layer [5][6]. The analysis process is divided into 7 steps as follows.…”

Section: Evaluation Principles Of Bp Neural Networkmentioning

confidence: 99%

“…The discrimination of main factors is displayed in table 1. The diseases grade of high tunnel leakage in Chongqing are divide into 4 grades in the aspect of tunnel leakage grade, based on standard and related references at home and aboard and the analysis of advantages and disadvantages of various division methods [3][4][5][6][7][8], considering the widely use of quartering method simultaneously.…”

Section: Building Of Evaluation Index Systemmentioning

confidence: 99%

Water Leakage Classification of Expressway Operationa Tunnel Based on Bp Neural Network

Zou¹,

He²,

Zhou³

et al. 2012

Proceedings of the 2nd International Conference on Electronic and Mechanical Engineering and Information Technology (2012)

View full text Add to dashboard Cite

Abstract. In this paper, factors influencing the tunnel leakage are analyzed synthetically, based on present situations of water leakage of operational highway tunnel in Chongqing area. Standard of tunnel leakage grade is determined and index system of tunnel leakage model is established by choosing physical geography, surrounding rock, underground water, lining and drainage facilities as the first grade indexes and choosing 12 factors such as vegetation, annual precipitation, and tunnel depth as the second indexes. Xiu-shan tunnel and Zheng-yang tunnel are selected as evaluation model of training sample from 66 operational tunnels in Chongqing area. The results are the consistent in comparing the neural network evaluation and manual evaluation. It is shown that this model has good applicability in grade evaluation of tunnel leakage, and classification of tunnel leakage could be done quickly and accurately.

show abstract

“…Basicamente, as redes neurais utilizadas para resolver problemas de otimização não-linear restrita são desenvolvidas utilizando parâmetros de penalidade (Kennedy & Chua, 1988;Vazquez et al, 1990;Zhang et al, 1992). Os pontos de equilíbrio destas redes, correspondentes às soluções do problema, são obtidos através de uma escolha adequada dos parâmetros de penalidade que devem ser suficientemente grandes para garantir a convergência da rede (Kennedy & Chua, 1988).…”

Section: Introductionunclassified

“…Os pontos de equilíbrio destas redes, correspondentes às soluções do problema, são obtidos através de uma escolha adequada dos parâmetros de penalidade que devem ser suficientemente grandes para garantir a convergência da rede (Kennedy & Chua, 1988). Entretanto, a escolha destes parâmetros é uma tarefa árdua, sendo normalmente realizada através de técnicas de tentativas e erros, as quais podem demandar um esforço computacional bastante excessivo.…”

Section: Introductionunclassified

Uma abordagem usando redes neurais artificiais para resolução de problemas de otimização restrita

2004

View full text Add to dashboard Cite

ResumoSistemas baseados em redes neurais artificiais fornecem altas taxas de computação devido ao uso de um número massivo de elementos processadores simples. Redes neurais com conexões realimentadas fornecem um modelo computacional capaz de resolver uma rica classe de problemas de otimização. Este artigo apresenta uma nova abordagem para resolver problemas de otimização restrita utilizando redes neurais artificiais. Mais especificamente, uma rede de Hopfield modificada é desenvolvida cujos parâmetros internos são calculados usando a técnica de subespaço válido de soluções. A partir da obtenção destes parâmetros a rede tende a convergir aos pontos de equilíbrio que representam as possíveis soluções para o problema. Exemplos de simulação são apresentados para justificar a validade da abordagem proposta.Palavras-chave: otimização restrita; redes neurais artificiais; redes de Hopfield. AbstractSystems based on artificial neural networks have high computational rates due to the use of a massive number of simple processing elements and the high degree of connectivity between these elements. Neural networks with feedback connections provide a computing model capable of solving a large class of optimization problems. This paper presents a novel approach for solving constrained optimization problems using artificial neural networks. More specifically, a modified Hopfield network is developed and its internal parameters are computed using the valid-subspace technique. These parameters guarantee the convergence of the network to the equilibrium points, which represent the feasible solutions to problem. Simulated examples are presented to demonstrate the validity of the proposed method.

show abstract

Neural networks for nonlinear programming

Cited by 1,030 publications

References 15 publications

Global Stability Analysis for a Class of Cohen-Grossberg Neural Network Models

Global Stability Analysis for a Class of Cohen-Grossberg Neural Network Models

Water Leakage Classification of Expressway Operationa Tunnel Based on Bp Neural Network

Uma abordagem usando redes neurais artificiais para resolução de problemas de otimização restrita

Contact Info

Product

Resources

About