Applying Online Gradient Descent Search to Genetic Programming for Object Recognition

Created by W.Langdon from gp-bibliography.bib Revision:1.7615

@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 = "ACSW Frontiers 2004

  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