The Modeling of the Rucklidge Chaotic System with Artificial Neural Networks

Chaotic systems are nonlinear that show sensitive dependence on initial conditions, and an immeasurably small change in value causes large the future state of system. Besides, there is no randomness chaotic they have order within themselves. Researchers use many areas such as mixer can make more homogeneous mixtures, encryption be used with high security, artificial neural networks by taking advantage this disorder. Differential equations which expressed mathematically solved numerical solution methods Heun, Euler, ODE45, RK4, RK5-Butcher Dormand-Prince literature. In research, Feed Forward Neural Network (FFNN), Layer Recurrent (LRNN) Cascade Backpropogation (CFNN) structures were to model Rucklidge system making MATLAB R2021A program (NN) Toolbox. By comparing results different activation functions modeling, ANN structure best has been determined. The training compared Artificial Networks (ANNs) was carried out values obtained from Euler method, get satisfactory fast results.