Solution of two-point fuzzy boundary value problems by fuzzy neural networks

• Main Authors: Mazin Hashim Suhhiem, Basim Nasih Abood, Mohammed Hadi Lafta
• Format: Article
• Language: English
• Published: Accademia Piceno Aprutina dei Velati 2019-06-01
• Series: Ratio Mathematica
• Subjects: two-point fuzzy boundary value problem; fully fuzzy neural network; fuzzy trial solution; minimized error function; hyperbolic tangent activation function
• Online Access: http://eiris.it/ojs/index.php/ratiomathematica/article/view/455

In this work, we have introduced a modified method for solving second-order fuzzy differential equations. This method based on the fully fuzzy neural network to find the numerical solution of the two-point fuzzy boundary value problems for the ordinary differential equations. The fuzzy trial solution of the two-point fuzzy boundary value problems is written based on the concepts of the fully fuzzy feed-forward neural networks which containing fuzzy adjustable parameters. In comparison with other numerical methods,  the proposed method provides numerical solutions with high accuracy.