Efficient recurrent neural network model for the solution of general nonlinear optimization problems

Malek, Alaeddin; Hosseinipour-Mahani, N.; Ezazipour, S.

doi:10.1080/10556780902856743

Cited by 19 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ANN application areas includes data classification and pattern recognition (Ripley, 1996), damage detection and earthquake simulation (Pei et al, 2006), function approximation (Toh, 1999;Ye and Lin, 2003), material science (Bhadeshia, 1999), experimental design of engineering systems (Röpke et al, 2005), nonlinear optimization (Malek et al, 2010), polypeptide structure prediction (Dorn and de Souza, 2010), prediction of trading signals of stock market indices (Tilakaratne et al, 2008), regression analysis (De Veux et al, 1998), signal and image processing (Watkin, 1993;Masters, 1994), time series analysis and forecasting (Franses and van Dijk, 2000;Kajitani et al, 2005).…”

Section: Discussionmentioning

confidence: 99%

Calibrating artificial neural networks by global optimization

Pintér

2012

Expert Systems with Applications

View full text Add to dashboard Cite

An artificial neural network (ANN) is a computational model − implemented as a computer program − that is aimed at emulating the key features and operations of biological neural networks. ANNs are extensively used to model unknown or unspecified functional relationships between the input and output of a "black box" system. In order to apply such a generic procedure to actual decision problems, a key requirement is ANN training to minimize the discrepancy between modeled and measured system output. In this work, we consider ANN training as a (potentially) multi-modal optimization problem. To address this issue, we introduce a global optimization (GO) framework and corresponding GO software. The practical viability of the GO based approach is illustrated by finding close numerical approximations of (one-dimensional, but non-trivial) functions.

show abstract

Section: Discussionmentioning

confidence: 99%

Calibrating artificial neural networks by global optimization

Pintér

2012

Expert Systems with Applications

View full text Add to dashboard Cite

show abstract

“…(15) From (14) and (15) we conclude that y * = (x * T , λ * T ) T is a solution of MNCP(G) when N = {1, 2, . .…”

Section: Connection Between Equilibrium Point and Global Solution Promentioning

confidence: 96%

“…(Malek et al [14]) A mixed nonlinear complementarity problem (MNCP) is finding a point x ∈ R n such that…”

Section: Problem Formulationmentioning

confidence: 99%

Solving a class of non-convex quadratic problems based on generalized KKT conditions and neurodynamic optimization technique

Malek¹,

Hosseinipour-Mahani²

2015

Kybernetika

View full text Add to dashboard Cite

“…The main purpose of using neural networks for solving various problems is to exploit their parallel processing nature and access to hardware implementations, which make it easier to deal with complex structures of considered problems [12,40]. Following the interesting work of Hopfield and Tank, the theory, methodology, and application of neural networks have been expanded to solve optimization problems [13,14,15,24,30,31,32].There are also several ANN models to solve bilevel problems and MPECs. Sheng et.…”

Section: Introductionmentioning

confidence: 99%