Accelerating neuro-evolution by compilation to native machine code

Created by W.Langdon from gp-bibliography.bib Revision:1.4192

  author =       "Nils T Siebel and Andreas Jordt and Gerald Sommer",
  title =        "Accelerating neuro-evolution by compilation to native
                 machine code",
  booktitle =    "International Joint Conference on Neural Networks
                 (IJCNN 2010)",
  year =         "2010",
  address =      "Barcelona, Spain",
  month =        "18-23 " # jul,
  publisher =    "IEEE Press",
  keywords =     "genetic algorithms, genetic programming",
  isbn13 =       "978-1-4244-6917-8",
  abstract =     "Any neuro-evolutionary algorithm that solves complex
                 problems needs to deal with the issue of computational
                 complexity. We show how a neural network (feed-forward,
                 recurrent or RBF) can be transformed and then compiled
                 in order to achieve fast execution speeds without
                 requiring dedicated hardware like FPGAs. The compiled
                 network uses a simple external data structure #x2014;a
                 vector #x2014;for its parameters. This allows the
                 weights of the neural network to be optimised by the
                 evolutionary process without the need to re-compile the
                 structure. In an experimental comparison our method
                 effects a speedup of factor 5 #x2013;10 compared to the
                 standard method of evaluation (i.e., traversing a data
                 structure with optimised C++ code)",
  DOI =          "doi:10.1109/IJCNN.2010.5596296",
  notes =        "WCCI 2010. Also known as \cite{5596296}",

Genetic Programming entries for Nils T Siebel Andreas Jordt Gerald Sommer