A capable neural network model for fuzzy quadratic optimization problems

In this paper, a representation of a recurrent neural network to solve fuzzy quadratic programming problems (FQP) is given. The motivation of the paper is to design a new effective one-layer structure recurrent neural network model for solving the FQP. Here, we reformulate the FQP to a bi-objective problem. Furthermore, the bi-objective problem is reduced to a weighting problem and then the Karush-Kuhn- Tucker (KKT) optimality conditions of the problem are constructed. A novel recurrent neural network model to solve the FQP is developed. Finally, an illustrative example is presented.