Genetic Generation of Both the Weights and Architecture for a Neural Network

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

@InProceedings{Koza91,
  author =       "John R. Koza and James P. Rice",
  title =        "Genetic Generation of Both the Weights and
                 Architecture for a Neural Network",
  booktitle =    "International Joint Conference on Neural Networks,
                 IJCNN-91",
  year =         "1991",
  volume =       "II",
  pages =        "397--404",
  address =      "Washington State Convention and Trade Center, Seattle,
                 WA, USA",
  publisher_address = "1109 Spring Street, Suite 300, Silver Spring, MD
                 20910, USA",
  month =        "8-12 " # jul,
  publisher =    "IEEE Computer Society Press",
  keywords =     "genetic algorithms, genetic programming,
                 connectionism, one-bit adder, cogann ref, LISP symbolic
                 expressions, connectivity, genetic programming, layers,
                 neural net architecture, neural net weights, one-bit
                 adder, performance, processing elements, LISP, digital
                 arithmetic, neural nets,",
  ISBN =         "0-7803-0164-1",
  LCCN =         "QA76.87.I57 1991b",
  bibdate =      "Wed Jan 15 14:07:16 1997",
  notes =        "Two volumes. IEEE catalog number: 91CH3049-4.",
  acknowledgement = ack-nhfb,
  URL =          "http://www.genetic-programming.com/jkpdf/ijcnn1991.pdf",
  DOI =          "doi:10.1109/IJCNN.1991.155366",
  abstract =     "This paper shows how to find both the weights and
                 architecture for a neural network (including the number
                 of layers, the number of processing elements per layer,
                 and the connectivity between processing elements). This
                 is accomplished using a recently developed extension to
                 the genetic algorithm which genetically breeds a
                 population of LISP symbolic expressions (S-expressions)
                 of varying size and shape until the desired performance
                 by the network is successfully evolved. The new genetic
                 programming paradigm is applied to the problem of
                 generating a neural network for the one-bit adder.",
  notes =        "IJCNN-91",
}

Genetic Programming entries for John Koza James P Rice

Citations