A Back Propagation-Type Neural Network Architecture for Solving the Complete n × n Nonlinear Algebraic System of Equations

The objective of this research is the presentation of a neural networkcapable of solving complete nonlinear algebraic systems of n equations with n unknowns. The proposed neural solver uses the classical back propagationalgorithm with the identity function as the output function, and supports thefeature of the adaptive learning rate for the neurons of the second hiddenlayer. The paper presents the fundamental theory associated with this approachas well as a set of experimental results that evaluate the performance andaccuracy of the proposed method against other methods found in the literature.