Deep Learning Application for Milne problem with linear anisotropic scattering

Using deep learning algorithms, which is a sub-branch of artificial intelligence, in this study, a deep learning model is developed according to both the number of secondary neutrons and the linear anisotropic scattering coefficient. These are independent variables that the dependent variable is the extrapolation distance. The training data set was calculated with HN method. ANN algorithm was written by TensorFlow and Keras which are the modules in Python programming language. The performance of the deep learning model for this problem has high performance so that the predicted new data which doesn’t be in the training data set is reliable according to the success of the model.