A parametric recurrent neural network scheme for solving a class of fuzzy regression models with some real-world applications

A cooperative neural dynamic model for solving general convex nonlinear optimization problems with fuzzy parameters and an application in manufacturing systems

“…There are several popular RNN's for constrained optimization which can be divided into the following two classes: First, the gradient based RNN's in References 30–41. Second, the projection type RNN's in References 42–59. Among gradient models, a globally convergent plan based on Fischer–Burmeister operators for solving second‐order cone constrained variational inequality problems by Nazemi and Sabeghi in Reference 32, by Nazemi and Mortezaee in Reference 33 for min‐max problems, for semidefinite programming problems by Nikseresht and Nazemi in Reference 36, by Miao et al 35 for efficiently solving nonlinear convex programs with second‐order cone constraints.…”

“…Among gradient models, a globally convergent plan based on Fischer–Burmeister operators for solving second‐order cone constrained variational inequality problems by Nazemi and Sabeghi in Reference 32, by Nazemi and Mortezaee in Reference 33 for min‐max problems, for semidefinite programming problems by Nikseresht and Nazemi in Reference 36, by Miao et al 35 for efficiently solving nonlinear convex programs with second‐order cone constraints. For projection models, Hu and Wang 42 for solving pseudo‐monotone variational inequalities and pseudo‐convex optimization problems examined a projection neural network, Arjmandzadeh et al 44 also studied a new neural network model for solving random interval linear programming problems, Effati et al 46 established a projection type neural network model to solve bilinear programming problems, He et al 50 introduced a projection type neural network model to solve variational inequalities, Mansoori et al 51 discussed on a model to solve the absolute value equations, Nikseresht and Nazemi 52,53 addressed two projection networks for linear and nonlinear semi‐definite programming problems, Karbasi et al 54,55 for fuzzy regression and Feizi and Nazemi 56 for stochastic support vector regression.…”

A Generalized Bridge Regression in Fuzzy Environment and Its Numerical Solution by a Capable Recurrent Neural Network

“…e aforesaid references in the main refer to a learning algorithm which is used to adjust the parameters of the feedforward fuzzy neural network. e although authors in [62] presented a hybrid scheme based on recurrent neural networks, and there is no record for solving the fuzzy bridge regression model by a neural network with stability and convergence properties. Furthermore, to obtain weighting coefficients, the authors use a recurrent procedure where the inverse of a matrix in each iteration needs to be computed explicitly.…”