Evolution of Optimal ANNs for Non-Linear Control Problems using Cartesian Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4504

  title =        "Evolution of Optimal ANNs for Non-Linear Control
                 Problems using Cartesian Genetic Programming",
  author =       "Maryam Mahsal Khan and Gul Muhammad Khan and 
                 Julian Francis Miller",
  booktitle =    "Proceedings of the 2010 International Conference on
                 Artificial Intelligence, {ICAI} 2010, July 12-15, 2010,
                 Las Vegas Nevada, {USA}, 2 Volumes",
  publisher =    "CSREA Press",
  year =         "2010",
  editor =       "Hamid R. Arabnia and David de la Fuente and 
                 Elena B. Kozerenko and Jos{\'e} Angel Olivas and Rui Chang and 
                 Peter M. LaMonica and Raymond A. Liuzzi and 
                 Ashu M. G. Solo",
  isbn13 =       "1-60132-148-1",
  pages =        "339--346",
  keywords =     "genetic algorithms, genetic programming, cartesian
                 genetic programming",
  URL =          "http://www.cartesiangp.co.uk/papers/icai2010-khan.pdf",
  size =         "8 pages",
  abstract =     "A method for evolving artificial neural networks using
                 Cartesian Genetic Programming (CGPANN) is proposed. The
                 CGPANN technique encodes the neural network attributes
                 namely weights, topology and functions and then evolves
                 them. The performance of the algorithm is evaluated on
                 the well known benchmark problem of double pole
                 balancing, a nonlinear control problem. The phenotype
                 of CGP is transformed into ANN and tested under various
                 conditions in the task environment. Results demonstrate
                 that CGPANN has the ability to generalise neural
                 architecture and parameters in substantially fewer
                 number of evaluations in comparison to earlier
                 neuroevolutionary techniques. We have also tested the
                 CGPANN for generalisation with different initial states
                 (not encountered during evolution) over a range of
                 evolved genotypes and obtained good results.",
  bibdate =      "2010-12-07",
  bibsource =    "DBLP,

Genetic Programming entries for Maryam Mahsal Khan Gul Muhammad Khan Julian F Miller