Neural-Network Based Physical Fields Modeling Techniques
The possibility of solving elliptic and parabolic partial differential equations by using cellular neural networks with specific structure is investigated. The method of solving varialble coefficients parabolic PDEs is proposed. Issues of cellular neural network stability are examined.
KeywordsNeural Network Feedforward Neural Network Cellular Neural Network Boundary Condition Type Mathematical Computer Modeling
Unable to display preview. Download preview PDF.
- 4.Wang, L., Mendel, J.M.: Structured trainable networks for matrix algebra. IEEE Int. Joint Conference on Neural Networks 2, 125–128 (1990)Google Scholar
- 7.Rekeczky, C., Szatmari, I., Foldesy, P., Roska, T.: Analogic Cellular PDE Machines. Analogical and Neural Computing Systems Laboratory. Computer and Automation Research Institute. Hungarian Academy of Sciences, Budapest, Hungary. Tech. Report, pp. 1–6 (2004)Google Scholar