Novel neural network based optimization approach for photonic devices

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.

[1]  T. Murphy,et al.  Vector Finite Difference Modesolver for Anisotropic Dielectric Waveguides , 2008, Journal of Lightwave Technology.

[2]  Jian-Ming Jin,et al.  Complex coordinate stretching as a generalized absorbing boundary condition , 1997 .

[3]  F. Vacca,et al.  Refinement and design of rare earth doped photonic crystal fibre amplifier using an ANN approach , 2011 .

[4]  Yiping Wang,et al.  Robust, compact, and flexible neural model for a fiber Raman amplifier , 2006 .

[5]  Francesco Prudenzano,et al.  A neural network model of erbium-doped photonic crystal fibre amplifiers , 2009 .

[6]  S. S. A. Obayya,et al.  Highly Nonlinear Birefringent Soft Glass Photonic Crystal Fiber With Liquid Crystal Core , 2011, IEEE Photonics Technology Letters.

[7]  B. M. A. Rahman,et al.  Design and characterization of compact single-section passive polarization rotator , 2001 .

[8]  B.M.A. Rahman,et al.  Vector beam propagation analysis of polarization conversion in periodically loaded waveguides , 2000, IEEE Photonics Technology Letters.

[9]  Michael Georgiopoulos,et al.  Applications of Neural Networks in Electromagnetics , 2001 .

[10]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[11]  Mohamed Farhat O Hameed,et al.  Design of passive polarization rotator based on silica photonic crystal fiber. , 2011, Optics letters.

[12]  John Moody,et al.  Fast Learning in Networks of Locally-Tuned Processing Units , 1989, Neural Computation.

[13]  S. Haxha,et al.  Photonic Crystal Fiber With an Ultrahigh Birefringence and Flattened Dispersion by Using Genetic Algorithms , 2013, Journal of Lightwave Technology.

[14]  O. Farle,et al.  Efficient Implementation of Non-Uniform Refinement Levels in a Geometric Multigrid Finite Element Method for Electromagnetic Waves , 2006, 2006 12th Biennial IEEE Conference on Electromagnetic Field Computation.

[15]  Wei-Ping Huang,et al.  Simulation of three-dimensional optical waveguides by a full-vector beam propagation method , 1993 .

[16]  B.M.A. Rahman,et al.  Beam propagation modeling of polarization rotation in deeply etched semiconductor bent waveguides , 2001, IEEE Photonics Technology Letters.

[17]  S. S. A. Obayya,et al.  Accurate radial basis function based neural network approach for analysis of photonic crystal fibers , 2008 .

[18]  B.M.A. Rahman,et al.  New full-vectorial numerically efficient propagation algorithm based on the finite element method , 2000, Journal of Lightwave Technology.

[19]  B. M. A. Rahman,et al.  Accurate finite element modal solution of photonic crystal fibres , 2005 .