Title :
Evolution of neural networks using Cartesian Genetic Programming
Author :
Khan, Maryam Mahsal ; Khan, Gul Muhammad ; Miller, Julian F.
Author_Institution :
Dept. of Comput. Syst. Eng., NWFP Univ. of Eng. & Technol., Peshawar, Pakistan
Abstract :
A novel Neuroevolutionary technique based on Cartesian Genetic Programming is proposed (CGPANN). ANNs are encoded and evolved using a representation adapted from the CGP. We have tested the new approach on the single pole balancing problem. Results show that CGPANN evolves solutions faster and of higher quality than the most powerful algorithms of Neuroevolution in the literature.
Keywords :
genetic algorithms; neural nets; Cartesian genetic programming; neural network evolution; neuroevolutionary technique; single pole balancing problem; Artificial neural networks; Encoding; Force; Genetic programming; Network topology; Neurons; Topology;
Conference_Titel :
Evolutionary Computation (CEC), 2010 IEEE Congress on
Conference_Location :
Barcelona
Print_ISBN :
978-1-4244-6909-3
DOI :
10.1109/CEC.2010.5586547
