Cellular Encoding Applied to Neurocontrol

Created by W.Langdon from gp-bibliography.bib Revision:1.7650

@InProceedings{whitley:1995:pole,

• 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 solve.",

}

Genetic Programming entries for L Darrell Whitley Frederic Gruau Larry D Pyeatt

Citations