- author = "Peter Nordin",
- title = "A Compiling Genetic Programming System that Directly Manipulates the Machine Code",
- booktitle = "Advances in Genetic Programming",
- publisher = "MIT Press",
- editor = "Kenneth E. {Kinnear, Jr.}",
- year = "1994",
- pages = "311--331",
- chapter = "14",
- keywords = "genetic algorithms, genetic programming, linear genetic programming, Machine code GP, Sun Spark, i868, X86",
-
URL = "
http://www.amazon.co.uk/Advances-Genetic-Programming-Complex-Adaptive/dp/0262111888",
- broken = "http://cognet.mit.edu/sites/default/files/books/9780262277181/pdfs/9780262277181_chap14.pdf",
-
DOI = "
10.7551/mitpress/1108.003.0019",
- size = "19 pages",
- abstract = "Most genetic programming approaches use a technique where a problem specific language is executed by an interpreter. The individual code segments in the population are decoded at run time by a virtual machine. The disadvantage of this paradigm is that interpreting the program involves a large overhead. Often the complete system and the genetic operators themselves are written in an interpreting language like LISP. This reduces performance in most hardware environments. We have evaluated the idea of using the lowest level native binary machine code as the programs in the population. There is no intermediate language or any interpreting steps. The genetic program that administers these machine code segments is written in the C-language. The algorithm is of steady state type and uses a small tournament as the selection mechanism. This approach has enhanced performance by a magnitude of three compared to a conventional system in an interpreting language. The increased performance is tested on a problem of symbolic regression of a classifier function in machine code. We evolved a machine code program that classifies Swedish words into nouns and non-nouns by spelling only. We compare the compiling genetic programming system (CGPS) with a Neural Network performing the same task. In our example, the results show superior performance of the CGPS compared to the connectionist approach. While the classification and generalisation capabilities were equal, the training time was more than 200 times faster, the classification time 500 times faster and the memory requirements are at least 10 times lower with the COPS, as compared with the Neural Network.",
-
notes = "Machine code GP Sun Spark and i868
Part of \cite{kinnear:book}",
