Solving fuzzy polynomial regression model with neural network

Polynomial regression as a special case of multiple linear regression is considered. A fuzzy version of the classical polynomial regression with fuzzy output and crisp inputs is presented. A neural network is constructed based on some concepts of convex optimization and stability theory, which guarantees to find the approximate parameters of the proposed model. A comparison between the fuzzy polynomial regression model and two other existing models with three different well-known fuzzy criteria is made. The numerical results clearly showed higher accuracy of the proposed fuzzy polynomial method compared to the other fuzzy polynomial regression (FPR) models

Keywords:

Fuzzy polynomial regression model , Recurrent neural network , Stability , Convergence , Affordable levels of house prices.