Improved Memetic Programming algorithm
Souhir Elleuch, Bassem Jarboui · International Journal of Operational Research · 2020
Automatic programming is an efficient technique that has contributed to an important development in the field of artificial intelligence. Genetic programming (GP) is a well known automatic programming algorithm based on genetic algorithm and evolves programs. In the present paper, we propose a new automatic programming method called two-dimensional memetic programming. It combines GP with local searches. We also introduce a new program representation for automatic programming algorithms. For this reason, the memetic programming algorithm is extended to evolve this program specific structure. To show the effectiveness of our method, we tested it on benchmark problems drawn from time series prediction and medical datasets classification, and we compared it with the related techniques.