Efficient Learning through Evolution: Neural Programming and Internal Reinforcement

Created by W.Langdon from gp-bibliography.bib Revision:1.4420

  author =       "Astro Teller and Manuela Veloso",
  title =        "Efficient Learning through Evolution: Neural
                 Programming and Internal Reinforcement",
  booktitle =    "Proceedings of the Seventeenth International
                 Conference on Machine Learning",
  month =        jul,
  year =         "2000",
  bib2html_pubtype = "Refereed Conference",
  bib2html_rescat = "Other",
  keywords =     "genetic algorithms, genetic programming",
  citeseer-isreferencedby = "oai:CiteSeerPSU:94197",
  annote =       "The Pennsylvania State University CiteSeer Archives",
  language =     "en",
  oai =          "oai:CiteSeerPSU:558985",
  rights =       "unrestricted",
  URL =          "http://www.cs.cmu.edu/~coral/publinks/mmv/icml00-astro.pdf",
  URL =          "http://citeseer.ist.psu.edu/558985.html",
  URL =          "http://citeseer.ist.psu.edu/330400.html",
  size =         "8 pages",
  abstract =     "Genetic programming (GP) can learn complex concepts by
                 searching for the target concept through evolution of
                 population of candidate hypothesis programs. However,
                 unlike some learning techniques, such as Artificial
                 neural networks (ANNs), GP does not have a principled
                 procedure for changing parts of a learned structure
                 based on that structure's performance on the training
                 data. GP is missing a clear, locally optimal update
                 procedure, an equivalent of gradient-descent
                 backpropagation for ANNs. This article introduces a new
                 mechanism, {"}internal reinforcement, {"} for defining
                 and using performance feedback on program evolution. A
                 new connectionist representation for evolving
                 parameterised programs, {"}neural programming{"} is
                 also introduced. We present the algorithms for the
                 generation of credit and blame assignment in the
                 process of learning programs using neural programming
                 and internal reinforcement. The article includes some
                 of our extensive experiments that demonstrate the
                 increased learning rate obtained by using our
                 principled program evolution approach.",
  notes =        "ICML 2000",

Genetic Programming entries for Astro Teller Manuela Veloso