In this paper, a new and an accurate artificial neural network approach (ANN) is presented for the analysis and design of photonic crystal fibers (PCFs). The new ANN approach is based on the radial basis functions which offer a very quick convergence and high efficiency during the ANN learning. The accuracy of the suggested approach is demonstrated via the excellent agreement between the results obtained using the presented approach and the results of the full vectorial finite difference method (FVFDM). In addition, a new design of highly birefringence PCF with low losses for the two polarized modes is presented using the proposed approach.
- neural networks
- finite difference method