Internal reinforcement in a connectionist genetic programming approach

Created by W.Langdon from gp-bibliography.bib Revision:1.3973

@Article{Teller:2000:AI,
  author =       "Astro Teller and Manuela Veloso",
  title =        "Internal reinforcement in a connectionist genetic
                 programming approach",
  journal =      "Artificial Intelligence",
  volume =       "120",
  pages =        "165--198",
  year =         "2000",
  number =       "2",
  month =        jul,
  keywords =     "genetic algorithms, genetic programming, Machine
                 learning, Evolutionary computation, Signal
                 understanding, Internal reinforcement, Neural
                 programming, Bucket brigade",
  URL =          "http://www.cs.cmu.edu/~coral/publinks/mmv/AIJ-Astro.pdf",
  broken =       "http://www.cs.cmu.edu/~coral/publications/b2hd-AIJ-Astro.html",
  URL =          "http://citeseer.ist.psu.edu/41715.html",
  URL =          "http://www.sciencedirect.com/science/article/B6TYF-40TY77M-1/1/c54fc0ab842b831a76c9e61e1c1c6b85",
  DOI =          "doi:10.1016/S0004-3702(00)00023-0",
  size =         "34 pages",
  abstract =     "Genetic programming (GP) can learn complex concepts by
                 searching for the target concept through evolution of a
                 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, the equivalent of gradient-descent
                 backpropagation for ANNs. This article introduces a new
                 algorithm, {"}internal reinforcement{"}, for defining
                 and using performance feedback on program evolution.
                 This internal reinforcement principled mechanism is
                 developed within a new connectionist representation for
                 evolving parameterized programs, namely {"}neural
                 programming{"}. 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 a
                 comprehensive overview of genetic programming and
                 empirical experiments that demonstrate the increased
                 learning rate obtained by using our principled program
                 evolution approach.",
  notes =        "oai:CiteSeerPSU:558697
                 http://citeseer.ist.psu.edu/558697.html gives a
                 slightly different version",
}

Genetic Programming entries for Astro Teller Manuela Veloso

Citations