Nuclear binding energy predictions using neural networks: Application of the multilayer perceptron

In recent years, artificial neural networks and their applications for large data sets have become a crucial part of scientific research. this work, we implement the Multilayer Perceptron (MLP), which is class feedforward network (ANN), to predict ground-state binding energies atomic nuclei. Two different MLP architectures with three four hidden layers are used study effects on predictions. To train architectures, two inputs along latest mass table changes in energy predictions also analyzed terms input channel. It seen that using appropriate putting more physical information channels, can make fast reliable nuclei, comparable microscopic density functionals.