[12p-N404-1~14] CS.2 3.3 情報フォトニクス・画像工学、4.4 Information Photonicsのコードシェアセッション

▲ [12p-N404-7] Machine learning approach to predict the output spectrum of different types of FBGs

〇(D)KOUSTAV DEY¹、V Nikhil¹、Sourabh Roy¹ (1.Nat. Inst. of Tech. WL)

キーワード：Optical Neural Network, Deep Learning, Optical Computing

In this paper, an artificial neural network (ANN) model is proposed to demonstrate the different type of fiber Bragg gratings (FBGs) using a single model at the first time to the best of our knowledge. For this purpose, mainly three different types of FBGs such as normal, π-phase-shifted and chirped FBG has been taken into consideration. An exact spectrum was able to reproduce using this proposed ANN model with a smaller time compared to using other simulation tools.