Grammatical Evolution: STE criterion in Symbolic Regression Task

Created by W.Langdon from gp-bibliography.bib Revision:1.4420

  title =        "Grammatical Evolution: STE criterion in Symbolic
                 Regression Task",
  author =       "R. Matousek",
  booktitle =    "Proceedings of the World Congress on Engineering and
                 Computer Science, WCECS '09",
  year =         "2009",
  editor =       "S. I. Ao and Craig Douglas and W. S. Grundfest and 
                 Jon Burgstone",
  volume =       "II",
  pages =        "1050--1054",
  address =      "San Francisco, USA",
  month =        oct # " 20-22",
  publisher =    "Newswood Limited",
  organization = "International Association of Engineers",
  keywords =     "genetic algorithms, genetic programming, grammatical
                 evolution, Grammatical Evolution, SSE, STE, Epsilon
                 Tube, Laplace Distribution",
  isbn13 =       "978-988-18210-2-7",
  URL =          "",
  size =         "5 pages",
  abstract =     "Grammatical evolution (GE) is one of the newest among
                 computational methods (Ryan et al., 1998
                 \cite{Ryan:1998:mendle}), (O'Neill and Ryan, 2001
                 \cite{oneill:2001:TEC}). Basically, it is a tool used
                 to automatically generate Backus-Naur-Form (BNF)
                 computer programs. The method's evolution mechanism may
                 be based on a standard genetic algorithm (GA). GE is
                 very often used to solve the problem of a symbolic
                 regression, determining a module's own parameters (as
                 it is also the case of other optimization problems) as
                 well as the module structure itself. A Sum Square Error
                 (SSE) method is usually used as the testing criterion.
                 In this paper, however, we will present the original
                 method, which uses a Sum Epsilon Tube Error (STE)
                 optimizing criterion. In addition, we will draw a
                 possible parallel between the SSE and STE criteria
                 describing the statistical properties of this new and
                 promising minimizing method.",
  notes =        "fitness like Koza's hits but minimum distance required
                 for a near miss is changed during GP run. Suggests STE
                 fitness follows Laplace (symmetric exponential)
                 [Equation 6 says Binomial?] distribution whilst sum of
                 errors squared follows Gaussian distribution. STE gives
                 smoother fit (fig 3 and fig4). Minitab. 2 one
                 dimensional problems. Lecture Notes in Engineering and
                 Computer Science",

Genetic Programming entries for Radomil Matousek