Applying Online Gradient Descent Search to Genetic Programming for Object Recognition

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@InProceedings{Zhang:04:AGDSGP,
  author =       "Will Smart and Mengjie Zhang",
  title =        "Applying Online Gradient Descent Search to Genetic
                 Programming for Object Recognition",
  booktitle =    "CRPIT '04: Proceedings of the second workshop on
                 Australasian information security, Data Mining and Web
                 Intelligence, and Software Internationalisation",
  year =         "2004",
  editor =       "James Hogan and Paul Montague and Martin Purvis and 
                 Chris Steketee",
  volume =       "32 no. 7",
  pages =        "133--138",
  address =      "Dunedin, New Zealand",
  publisher =    "Australian Computer Society, Inc.",
  publisher_address = "PO Box Q534, QVB Post Office, Sydney 1230,
                 Australia",
  month =        jan,
  keywords =     "genetic algorithms, genetic programming, data mining,
                 machine learning, object classification",
  ISBN =         "1-920682-14-7",
  URL =          "http://crpit.com/confpapers/CRPITV32Smart.pdf",
  URL =          "http://portal.acm.org/citation.cfm?id=976440.976460",
  size =         "6 pages",
  abstract =     "the use of gradient descent search in genetic
                 programming (GP) for object classification problems. In
                 this approach, pixel statistics are used to form the
                 feature terminals and a random generator produces
                 numeric terminals. The four arithmetic operators and a
                 conditional operator form the function set and the
                 classification accuracy is used as the fitness
                 function. In particular, gradient descent search is
                 introduced to the GP mechanism and is embedded into the
                 genetic beam search, which allows the evolutionary
                 learning process to globally follow the beam search and
                 locally follow the gradient descent search. This method
                 is compared with the basic GP method on four image data
                 sets with object classification problems of increasing
                 difficulty. The results show that the new method
                 outperformed the basic GP method on all cases in both
                 classification accuracy and training time, suggesting
                 that the GP method with the gradient descent search is
                 more effective and more efficient than without on
                 object classification problems.",
  notes =        "Chained Rules in Genetic Programs differentiation, NZ
                 coin dataset

                 School of Mathematical and Computer Science Victoria
                 University of Wellington, P. O. Box 600, Wellington,
                 New Zealand Email:
                 fsmartwill,mengjieg@mcs.vuw.ac.nz

                 Also Australian Computer Science Communications, Vol.
                 26, No. 7. http://crpit.com/Vol32.html",
}

Genetic Programming entries for Will Smart Mengjie Zhang

Citations