A Comparison of Evolvable Hardware Architectures for Classification Tasks

Created by W.Langdon from gp-bibliography.bib Revision:1.4496

  author =       "Kyrre Glette and Jim Torresen and Paul Kaufmann and 
                 Marco Platzner",
  title =        "A Comparison of Evolvable Hardware Architectures for
                 Classification Tasks",
  booktitle =    "8th International Conference on Evolvable Systems:
                 From Biology to Hardware: ICES 2008",
  year =         "2008",
  editor =       "Gregory S. Hornby and Lukas Sekanina and 
                 Pauline C. Haddow",
  volume =       "5216",
  series =       "LNCS",
  pages =        "22--33",
  address =      "Prague, Czech Republic",
  month =        sep # " 21-24",
  publisher =    "Springer",
  keywords =     "genetic algorithms, genetic programming",
  isbn13 =       "978-3-540-85857-7",
  DOI =          "doi:10.1007/978-3-540-85857-7_3",
  size =         "12 pages",
  abstract =     "We analyse and compare four different evolvable
                 hardware approaches for classification tasks: An
                 approach based on a programmable logic array
                 architecture, an approach based on two-phase
                 incremental evolution, a generic logic architecture
                 with automatic definition of building blocks, and a
                 specialized coarse-grained architecture with
                 pre-defined building blocks. We base the comparison on
                 a common data set and report on classification accuracy
                 and training effort. The results show that
                 classification accuracy can be increased by using
                 modular, specialized classifier architectures.
                 Furthermore, function level evolution, either with
                 predefined functions derived from domain-specific
                 knowledge or with functions that are automatically
                 defined during evolution, also gives higher accuracy.
                 Incremental and function level evolution reduce the
                 search space and thus shortens the training effort.",

Genetic Programming entries for Kyrre Harald Glette Jim Torresen Paul Kaufmann Marco Platzner