Neutrality and Epistasis in Program Space

Created by W.Langdon from gp-bibliography.bib Revision:1.4504

@InProceedings{Renzullo:2018:GI,
  author =       "Joseph Renzullo and Westley Weimer and 
                 Melanie Moses and Stephanie Forrest",
  title =        "Neutrality and Epistasis in Program Space",
  booktitle =    "GI-2018, ICSE workshops proceedings",
  year =         "2018",
  editor =       "Justyna Petke and Kathryn Stolee and 
                 William B. Langdon and Westley Weimer",
  pages =        "1--8",
  address =      "Gothenburg, Sweden",
  month =        "2 " # jun,
  publisher =    "ACM",
  publisher_address = "New York, NY, USA",
  note =         "Best Presentation Award",
  keywords =     "genetic algorithms, genetic programming, genetic
                 improvement, SBSE, Software evolution, Network science,
                 Biological networks, Software testing and debugging,
                 Automated software engineering",
  isbn13 =       "978-1-4503-5753-1",
  URL =          "http://geneticimprovementofsoftware.com/wp-content/uploads/2018/04/Renzullo_2018_GI.pdf",
  DOI =          "doi:10.1145/3194810.3194812",
  size =         "8 pages",
  abstract =     "Neutral networks in biology often contain diverse
                 solutions with equal fitness, which can be useful when
                 environments (requirements) change over time. we
                 present a method for studying neutral networks in
                 software. In these networks, we find multiple solutions
                 to held-out test cases (latent bugs), suggesting that
                 neutral software networks also exhibit relevant
                 diversity. We also observe instances of positive
                 epistasis between random mutations, i.e. interactions
                 that collectively increase fitness. Positive epistasis
                 is rare as a fraction of the total search space but
                 significant as a fraction of the objective space:
                 9percent of the repairs we found to look (and
                 4.63percent across all programs analysed) were produced
                 by positive interactions between mutations. Further,
                 the majority (62.50percent) of unique repairs are
                 instances of positive epistasis",
  notes =        "high order mutation in C code (2-edit epistasis). Unix
                 look utility. ccrypt, look, merge, units, zune

                 Slides:
                 http://geneticimprovementofsoftware.com/wp-content/uploads/2018/06/Renzullo.pdf

                 GI-2018 http://geneticimprovementofsoftware.com part of
                 \cite{Petke:2018:ICSEworkshop}",
}

Genetic Programming entries for Joseph Renzullo Westley Weimer Melanie Moses Stephanie Forrest

Citations