Learning Weights in Genetic Programs Using Gradient Descent for Object Recognition

Created by W.Langdon from gp-bibliography.bib Revision:1.4549

  author =       "Mengjie Zhang and Will Smart",
  title =        "Learning Weights in Genetic Programs Using Gradient
                 Descent for Object Recognition",
  booktitle =    "Applications of Evolutionary Computing,
                 EvoWorkshops2005: {EvoBIO}, {EvoCOMNET}, {EvoHOT},
                 {EvoIASP}, {EvoMUSART}, {EvoSTOC}",
  year =         "2005",
  month =        "30 " # mar # "-1 " # apr,
  editor =       "Franz Rothlauf and Juergen Branke and 
                 Stefano Cagnoni and David W. Corne and Rolf Drechsler and 
                 Yaochu Jin and Penousal Machado and Elena Marchiori and 
                 Juan Romero and George D. Smith and Giovanni Squillero",
  series =       "LNCS",
  volume =       "3449",
  publisher =    "Springer Verlag",
  address =      "Lausanne, Switzerland",
  publisher_address = "Berlin",
  pages =        "417--427",
  keywords =     "genetic algorithms, genetic programming, evolutionary
  ISBN =         "3-540-25396-3",
  ISSN =         "0302-9743",
  DOI =          "doi:10.1007/b106856",
  abstract =     "the use of gradient descent search in tree based
                 genetic programming for object recognition problems. A
                 weight parameter is introduced to each link between two
                 nodes in a program tree. The weight is defined as a
                 floating point number and determines the degree of
                 contribution of the sub-program tree under the link
                 with the weight. Changing a weight corresponds to
                 changing the effect of the sub-program tree. The weight
                 changes are learnt by gradient descent search at a
                 particular generation. The programs are evolved and
                 learned by both the genetic beam search and the
                 gradient descent search. This approach is examined and
                 compared with the basic genetic programming approach
                 without gradient descent on three object classification
                 problems of varying difficulty. The results suggest
                 that the new approach works well on these problems.",
  notes =        "EvoWorkshops2005",

Genetic Programming entries for Mengjie Zhang Will Smart