Abstract—Artificial Intelligence (AI) techniques of artificial neural networks (ANN) and evolutionary computation of genetic programming (GP) have recently been used to design and implement more effective models. The artificial neural network (ANN) model has been used to study the charged particles multiplicity distributions for antiproton-neutron ( p - n - ) and proton-neutron ( p - n) collisions at different lab momenta. The neural network model performance was also tested at non-trained space (predicted) and matched them effectively. The trained NN shows a good fitting with the available experimental data. The NN simulation results prove a solid existence in modeling hadronic collisions. Genetic Programming (GP) model is a flexible and powerful technique that can be used for solving the same problem. In this paper, genetic programming (GP) has been used to discover a function that calculates the charged particles multiplicity distribution of created pions for the same interactions at high energies. The predicted distributions from the GP-based model are compared with the available experimental data. The discovered function of GP model has proven an excellent matching with the corresponding experimental data.

Index Terms—Artificial intelligence technique, genetic programming, hadronic collisions, machine learning (ML), multiplicity distribution, neural network, pion production.

Moaaz A. Moussa is with the Buraydah Colleges, Al-Qassim, Buraydah, King Abdulazziz Road, East Qassim University, P.O.Box 31717, Kingdom of Saudi Arabia (e-mail: moaaz2030@yahoo.com).

Cite: Moaaz A. Moussa, "High Energy Hadronic Collisions Using Neural Network and Genetic Programming Techniques," International Journal of Applied Physics and Mathematics  vol. 3, no. 2, pp. 146-151, 2013.