Flight of the FINCH through the Java Wilderness

Created by W.Langdon from gp-bibliography.bib Revision:1.4524

  title =        "Flight of the {FINCH} through the {Java} Wilderness",
  author =       "Michael Orlov and Moshe Sipper",
  journal =      "IEEE Transactions on Evolutionary Computation",
  year =         "2011",
  volume =       "15",
  number =       "2",
  pages =        "166--182",
  month =        apr,
  keywords =     "genetic algorithms, genetic programming, Automatic
                 programming, Java bytecode, software evolution",
  ISSN =         "1089-778X",
  URL =          "https://drive.google.com/file/d/0B6G3tbmMcpR4bFVYbWRWVGlDN28/view",
  DOI =          "doi:10.1109/TEVC.2010.2052622",
  size =         "17 pages",
  abstract =     "We describe Fertile Darwinian Bytecode Harvester
                 (FINCH), a methodology for evolving Java bytecode,
                 enabling the evolution of extant, unrestricted Java
                 programs, or programs in other languages that compile
                 to Java bytecode. Our approach is based upon the notion
                 of compatible crossover, which produces correct
                 programs by performing operand stack-based, local
                 variables-based, and control flow-based compatibility
                 checks on source and destination bytecode sections.
                 This is in contrast to existing work that uses
                 restricted subsets of the Java bytecode instruction set
                 as a representation language for individuals in genetic
                 programming. We demonstrate FINCH's unqualified success
                 at solving a host of problems, including simple and
                 complex regression, trail navigation, image
                 classification, array sum, and tic-tac-toe. FINCH
                 exploits the richness of the Java virtual machine
                 architecture and type system, ultimately evolving
                 human-readable solutions in the form of Java programs.
                 The ability to evolve Java programs will hopefully lead
                 to a valuable new tool in the software engineer's
  notes =        "Many crossovers tried for each good one. Gaussian
                 distribution of byte code segment sizes. Mutation of

                 Byte code instrumented to prevent infinite
                 loops/recursions. No protection or closure. Whole
                 initial population clones of man made seed. Parsimony
                 via fitness function. ASM ECJ. Symbolic regression,
                 Santa Fe trail artificial ant, intertwined spirals,
                 array sum, tic-tac-toe (negamaxab).

                 Intertwined Spirals mentioned on GP discussion list 8
                 Oct 2017

                 Entered 2010 HUMIES GECCO 2010

                 Also known as \cite{5685268}",

Genetic Programming entries for Michael Orlov Moshe Sipper