OICC Press International Nano Letters 2228-5326 6 3 (September 2016) 2016 06 08 Modeling of relative intensity noise and terminal electrical noise of semiconductor lasers using artificial neural network 10.1007/s40089-016-0180-0 EN A. Rezaei Electrical Engineering Department, Kermanshah University of Technology, Kermanshah, IR L. Noori Electrical Engineering Department, Kermanshah University of Technology, Kermanshah, IR Journal Article 2016 06 08 Abstract In this paper, artificial neural network (ANN) is used to predict the source laser’s relative intensity noise (RIN) and the terminal electrical noise (TEN) of semiconductor lasers. For this purpose, the multi-layer perceptron (MLP) neural network trained with the back propagation algorithm is used. To develop this model, the normalized bias current and frequency are selected as the input parameters and the RIN and TEN of semiconductor lasers are selected as the output parameters. The obtained results show that the proposed ANN model is in a good agreement with the numerical method, and a small error between the predicted values and the numerical solution is obtained. Therefore, the proposed ANN model is a useful, reliable, fast and cheap tool to predict the RIN and TEN of semiconductor lasers.