Applying Online Gradient Descent Search to Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.4524

  author =       "Will Smart and Mengjie Zhang",
  title =        "Applying Online Gradient Descent Search to Genetic
  institution =  "Computer Science, Victoria University of Wellington",
  year =         "2003",
  number =       "CS-TR-03-13",
  address =      "New Zealand",
  keywords =     "genetic algorithms, genetic programming",
  URL =          "",
  URL =          "",
  abstract =     "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

Genetic Programming entries for Will Smart Mengjie Zhang