Gene Expression Programming and Artficial Neural Network Approaches for Event Selection in High Energy Physics

摘要

Gene Expression Programming is a new evolutionary algorithm found to be very efficient for solving benchmark problems from computer science. The algorithm was also successfully tested for event selection in high energy physics data analysis. This paper presents an extended event selection analysis with this algorithm, as well as a comparison of its results with those obtained with an artificial neural network. Both methods produced selection functions that allowed high classification accuracies, around 95%.