License: Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/DagSemProc.08051.5
URN: urn:nbn:de:0030-drops-14838
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2008/1483/
Go to the corresponding Portal


McPhee, Nicholas Freitag ; Poli, Riccardo

N-gram GP: Early results and half-baked ideas

pdf-format:
08051.McPheeNicholasFreitag.ExtAbstract.1483.pdf (0.02 MB)


Abstract

In this talk I present N-gram GP, a system for evolving linear GP programs using an EDA style system to update the probabilities of different 3-grams (triplets) of instructions. I then pick apart some of the evolved programs in an effort to better understand the properties of this approach and identify ways that it might be extended.

Doing so reveals that there are frequently cases where the system needs two triples of the form ABC and ABD to solve the problem, but can only choose between them probabilistically in the EDA phase. I present the entirely untested idea of creating a new pseudo-instruction that is a duplicate of a key instruction. This could potentially allow the system to learn, for example, that AB is always followed by C, while AB' is always followed by D.


BibTeX - Entry

@InProceedings{mcphee_et_al:DagSemProc.08051.5,
  author =	{McPhee, Nicholas Freitag and Poli, Riccardo},
  title =	{{N-gram GP: Early results and half-baked ideas}},
  booktitle =	{Theory of Evolutionary Algorithms},
  pages =	{1--3},
  series =	{Dagstuhl Seminar Proceedings (DagSemProc)},
  ISSN =	{1862-4405},
  year =	{2008},
  volume =	{8051},
  editor =	{Dirk V. Arnold and Anne Auger and Jonathan E. Rowe and Carsten Witt},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2008/1483},
  URN =		{urn:nbn:de:0030-drops-14838},
  doi =		{10.4230/DagSemProc.08051.5},
  annote =	{Keywords: Genetic programming, estimation of distribution algorithms, linear GP, machine learning}
}

Keywords: Genetic programming, estimation of distribution algorithms, linear GP, machine learning
Collection: 08051 - Theory of Evolutionary Algorithms
Issue Date: 2008
Date of publication: 06.05.2008


DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI