A Computational Design-Based Scale Conjugate Neural Network to Solve the Nonlinear Rabinovich–Fabrikant Model

This research provides a design of a computational framework using the scale conjugate gradient neural network (SCGDNN) for solving a nonlinear Rabinovich–Fabrikant model. The mathematical differential form of the nonlinear model has three classes [Formula: see text], [Formula: see text] and [Formula: see text], which are solved by applying the stochastic SCGDNN. An Adam approach is used to get the dataset in order to reduce the mean square error with the division of the data 70% for training, while 15%, 15% for authorization and testing. Seventeen neurons, an activation log-sigmoid function and a single-layer feed-forward neural network are proposed to solve the Rabinovich–Fabrikant model. By comparing the generated outputs with reference (Runge–Kutta) results, one can determine the validity of the proposed neural network. Furthermore, the precision of the designed neural computing network is judged by applying different performances of error histogram, correlation and state transition. The supervised SCGDNN has never been exploited before for solving the nonlinear Rabinovich–Fabrikant model.