الفهرس 
IntroductionOnly 14 pages are availabe for public view
 |  | from | 80 |  |  |
| | | from | 80 | | |
Abstract
Machine learning (ML) is the study of computer algorithms that can be improved automatically through experience and the used data. Machine learning algorithms build a model based on sample data that are used in a wide variety of applications, such as in medicine, email filtering, and speech recognition, where it is difficult to develop conventional algorithms to perform the needed tasks. On the other hand, ML is a subfield of artificial intelligence while deep learning is a subfield of machine learning. Further, the neural network makes up the backbone of deep learning algorithms. In the present work, we use the cellular neural network (CNN), as an example of ML, to solve two vital nonlinear partial differential equations (NLPDEqs). The first equation is the Zakharov Kuznetsov Burger (ZKB) equation which is obtained using the reductive perturbation technique for a dusty plasma system, in which electrons obey the hybrid Cairns-Tsallis distribution while dust particles and ions are inertial. Then, the CNN algorithm is integrated with the finite difference method to simulate the ZKB equation with a high accuracy. The obtained solution is approximately identical to the analytical solution which is obtained via the Tanh method. An algorithm to solve ZKB equation using the finite difference method is employed to asses the accuracy of the CNN algorithm. Moreover, it is found that the plasma parameters (viscosity coefficients, cyclotron frequency; nonextensive parameter,...etc.) have significant effects on the shock wave characteristics. Hence, CNN is implemented to investigate the features of dust ion acoustic shock waves in a two-fluid model of magnetized dusty plasma. The second equation is obtained for Langmuir waves in a fully degenerate ultrarelativistic plasma consisting of hot electrons and cold ions. The state equation for this plasma system and quantum hydrodynamic (QHD) model are used to derive a nonlinear differential evolution equation for the chemical potential that described these waves in a plasma system. It is found that the ordinary electronic oscillations, similar to the classical oscillations, occur along with small scale quantum Langmuir oscillations induced by the Bohm quantum force. We use the Runge Kutta to solve the nonlinear differential equation, governing the system These investigations.