Evolving Weights in Genetic Programs Using Gradient Descent

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

  author =       "Will Smart and Mengjie Zhang",
  title =        "Evolving Weights in Genetic Programs Using Gradient
  institution =  "Computer Science, Victoria University of Wellington",
  year =         "2004",
  number =       "CS-TR-04-11",
  address =      "New Zealand",
  keywords =     "genetic algorithms, genetic programming",
  URL =          "http://www.mcs.vuw.ac.nz/comp/Publications/archive/CS-TR-04/CS-TR-04-11.pdf",
  URL =          "http://www.mcs.vuw.ac.nz/comp/Publications/CS-TR-04-11.abs.html",
  abstract =     "gradient descent search in tree based genetic
                 programming for object recognition problems. To learn
                 better partial programs, a weight parameter is
                 introduced in each link between every two nodes in a
                 program tree, so that a change of a weight corresponds
                 to a change of the effect of the sub-program tree.
                 Inside a particular generation, weight changes are
                 learnt locally by gradient descent search, but the
                 whole evolution process is still carried out across
                 different generations globally by the genetic beam
                 search. This approach is examined and compared with the
                 basic genetic programming approach without gradient
                 descent on three object classification problems of
                 various difficulty. The results suggest that the new
                 approach outperforms the basic approach on all

Genetic Programming entries for Will Smart Mengjie Zhang