Shortcomings with using edge encodings to represent graph structures

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@Article{Hornby:2006:GPEM,
  author =       "Gregory S. Hornby",
  title =        "Shortcomings with using edge encodings to represent
                 graph structures",
  journal =      "Genetic Programming and Evolvable Machines",
  year =         "2006",
  volume =       "7",
  number =       "3",
  pages =        "231--252",
  month =        oct,
  keywords =     "genetic algorithms, genetic programming, Circuits,
                 Graphs, Neural networks, Representations, CEEL, PEEL,
                 ANN",
  ISSN =         "1389-2576",
  URL =          "http://ic.arc.nasa.gov/publications/pdf/1212.pdf",
  DOI =          "doi:10.1007/s10710-006-9007-5",
  abstract =     "There are various representations for encoding graph
                 structures, such as artificial neural networks (ANNs)
                 and circuits, each with its own strengths and
                 weaknesses. Here we analyse edge encodings and show
                 that they produce graphs with a node creation order
                 connectivity bias (NCOCB). Additionally, depending on
                 how input/ output (I/O) nodes are handled, it can be
                 difficult to generate ANNs with the correct number of
                 I/O nodes. We compare two edge encoding languages, one
                 which explicitly creates I/O nodes and one which
                 connects to pre-existing I/O nodes with parameterised
                 connection operators. Results from experiments show
                 that these parameterized operators greatly improve the
                 probability of creating and maintaining networks with
                 the correct number of I/O nodes, remove the
                 connectivity bias with I/O nodes and produce better
                 ANNs. These results suggest that evolution with a
                 representation which does not have the NCOCB will
                 produce better performing ANNs. Finally we close with a
                 discussion on which directions hold the most promise
                 for future work in developing better representations
                 for graph structures.",
  notes =        "3-parity. goal scoring robot",
}

Genetic Programming entries for Gregory S Hornby

Citations