Cellular Encoding Applied to Neurocontrol

Created by W.Langdon from gp-bibliography.bib Revision:1.4420

  author =       "Darrell Whitley and Frederic Gruau and Larry Pyeatt",
  title =        "Cellular Encoding Applied to Neurocontrol",
  booktitle =    "Genetic Algorithms: Proceedings of the Sixth
                 International Conference (ICGA95)",
  year =         "1995",
  editor =       "Larry J. Eshelman",
  pages =        "460--467",
  address =      "Pittsburgh, PA, USA",
  publisher_address = "San Francisco, CA, USA",
  month =        "15-19 " # jul,
  publisher =    "Morgan Kaufmann",
  keywords =     "genetic algorithms, genetic programming",
  ISBN =         "1-55860-370-0",
  URL =          "http://www.cs.colostate.edu/~genitor/1995/poles.pdf",
  size =         "8 pages",
  abstract =     "Neural networks are trained for balancing 1 and 2
                 poles attached to a cart on a fixed track. For one
                 variant of the single pole system, only pole angle and
                 cart position variables are supplied as inputs; the
                 network must learn to compute velocities. All of the
                 problems are solved using a fixed architecture and
                 using a new version of cellular encoding that evolves
                 an application specific architecture with real-valued
                 weights. The learning times and generalization
                 capabilities are compared for neural networks developed
                 using both methods. After a post processing
                 simplification, topologies produced by cellular
                 encoding were very simple and could be analysed.
                 Architectures with no hidden units were produced for
                 the single pole and the two pole problem when velocity
                 information is supplied as an input. Moreover, these
                 linear solutions display good generalization. For all
                 the control problems, cellular encoding can
                 automatically generate architectures whose complexity
                 and structure reflect the features of the problem to

Genetic Programming entries for L Darrell Whitley Frederic Gruau Larry Pyeatt