“…One promising approach for solving optimization problems in real time is to use neural networks (see, e.g., Tank & Hopfield, 1986;Maa & Shanblatt, 1992;Wang, 1993). In the past two decades, many recurrent neural network models have been developed for solving linear and nonlinear programming problems, demonstrating many computational advantages (see, e.g., Forti & Tesi, 1995;Zak, Upatising, & Hui, 1995;Xia & Wang, 2000;Leung, Chen, Jiao, Gao, & Leung, 2001;Xia, 2004;Xia & Feng, 2005;Gao & Liao, 2006;Xia & Ye, 2008;Liu & Wang, 2008a). In particular, Tank and Hopfield (1986) proposed a recurrent neural network for solving linear programming problems, which opened the avenue of solving optimization problems by using recurrent neural networks.…”