- author = "Ronald L. Crepeau",
- title = "Genetic Evolution of Machine Language Software",
- booktitle = "Proceedings of the Workshop on Genetic Programming: From Theory to Real-World Applications",
- year = "1995",
- editor = "Justinian P. Rosca",
- pages = "121--134",
- address = "Tahoe City, California, USA",
- month = "9 " # jul,
- keywords = "genetic algorithms, genetic programming, memory",
-
URL = "
http://www.cs.ucl.ac.uk/staff/W.Langdon/ftp/papers/GEMS_Article.pdf",
- size = "14 pages",
- abstract = "Genetic Programming (GP) has a proven capability to routinely evolve software that provides a solution function for the specified problem. Prior work in this area has been based upon the use of relatively small sets of pre-defined operators and terminals germane to the problem domain. This paper reports on GP experiments involving a large set of general purpose operators and terminals. Specifically, a microprocessor architecture with 660 instructions and 255 bytes of memory provides the operators and terminals for a GP environment. Using this environment, GP is applied to the beginning programmer problem of generating a desired string output, e.g., {"}Hello World{"}. Results are presented on: the feasibility of using this large operator set and architectural representation; and, the computations required to breed string outputting programs vs. the size of the string and the GP parameters employed.",
-
notes = "Z80 Machine code evolved to write {"}Hello World{"}
HWP 660 instructions and 255 byte RAM (modular
arithmetic used to address indexed memory)
GEMS genetic evolution of machine language software Breeding system similar to crowding and Tackett's Softbrood selection (max litter size of 12). GA like crossover acts on code and contents of memory. Pool of 1500 member 0.20 mutation rate.
{"}indicates that the problem difficulty, over the range of the test and in terms of required spawns, while increasing rapidly, does not appear to be combinatorial or exponential{"} (suggests O(n**3) ).
Discussion of statistics of number of useful terminals in random and later populations.
Memory initialised to random values. {"}Cultural memory{"} cf \cite{spector:1996:ctiGP}.
Steady state GA. 2 types of Mutation (20 percent). While JP jump and subroutines are discussed the problem does not need iteration to solve it.
part of \cite{rosca:1995:ml}",
