Routine high-return human-competitive machine learning

Created by W.Langdon from gp-bibliography.bib Revision:1.4221

  author =       "John R. Koza",
  title =        "Routine high-return human-competitive machine
  booktitle =    "Proceedings of the International Conference on Machine
                 Learning and Applications",
  year =         "2003",
  editor =       "M. Arif Wani and K. Cois and K. Hafeez",
  pages =        "6--12",
  address =      "Los Angeles",
  keywords =     "genetic algorithms, genetic programming, machine
                 learning, automated invention, parameterized topology,
  URL =          "",
  size =         "7 pages",
  abstract =     "Genetic programming is a systematic method for getting
                 computers to automatically solve a problem. Genetic
                 programming starts from a high-level statement of what
                 needs to be done and automatically creates a computer
                 program to solve the problem. The paper makes the
                 points that (1) genetic programming now routinely
                 delivers high-return human-competitive machine
                 intelligence; (2) it is an automated invention machine;
                 (3) it can automatically create a general solution to a
                 problem in the form of a parameterised topology; and
                 (4) it has delivered a progression of qualitatively
                 more substantial results in synchrony with five
                 approximately order-of-magnitude increases in the
                 expenditure of computer time.",

Genetic Programming entries for John Koza