Novel neural network based optimization approach for photonic devices

Abstract

In this paper, a novel optimization technique is proposed for designing photonic devices. The suggested approach relies on the use of radial bases function based artificial neural network (RBF-ANN) which shows an excellent performance in comparison with the conventional artificial neural network technique. The robustness of the suggested RBF-ANN approach is demonstrated through the numerical precision and fast convergence of the design cycle performed on a typical slanted rib waveguide polarization rotator, and ultra-flattened zero dispersion photonic crystal fiber.