ARTIFICIAL NEURAL NETWORK AND GENETIC ALGORITHM HYBRID TECHNIQUE FOR NUCLEUS-NUCLEUS COLLISIONS

摘要

Selecting the optimal topology of a neural network for a particular application is a difficult task. Genetic Algorithm (GA) has been used to find the optimal neural network (NN) solution (i.e., hybrid technique) to calculate the pseudo-rapidity distribution of the shower particles for C-12, O-16, Si-28, and S-32 on nuclear emulsion. An efficient NN has been designed by GA to predict the distributions that are not present in the training set and matched them effectively. The proposed method shows a better fitting with experimental data. The hybrid technique GA-ANN simulation results prove a strong presence modeling in heavy ion collisions.