Analysis of Schema Frequencies in Genetic Programming

Bogdan Burlacu; Michael Affenzeller; Michael Kommenda; Gabriel Kronberger; Stephan M. Winkler

Analysis of Schema Frequencies in Genetic Programming

Bogdan Burlacu, Michael Affenzeller, Michael Kommenda, Gabriel Kronberger, Stephan M. Winkler

Institute of Formal Models and Verification

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

Abstract

Genetic Programming (GP) schemas are structural templates equivalent to hyperplanes in the search space. Schema theories provide information about the properties of subsets of the population and the behavior of genetic operators. In this paper we propose a practical methodology to identify relevant schemas and measure their frequency in the population. We demonstrate our approach on an artificial symbolic regression benchmark where the parts of the formula are already known. Experimental results reveal how solutions are assembled within GP and explain diversity loss in GP populations through the proliferation of repeated patterns.

Original language	English
Title of host publication	Lecture Notes in Computer Science
Editors	R. Moreno-Diaz, F.R. Pichler, A. Quesada-Arencibia
Number of pages	7
Publication status	Published - 2017

Fields of science

102 Computer Sciences
102001 Artificial intelligence
102011 Formal languages
102022 Software development
102031 Theoretical computer science
603109 Logic
202006 Computer hardware

JKU Focus areas

Computation in Informatics and Mathematics

Cite this

@inbook{c0add97af9534939a3b22be13a1d81e5,

title = "Analysis of Schema Frequencies in Genetic Programming",

abstract = "Genetic Programming (GP) schemas are structural templates equivalent to hyperplanes in the search space. Schema theories provide information about the properties of subsets of the population and the behavior of genetic operators. In this paper we propose a practical methodology to identify relevant schemas and measure their frequency in the population. We demonstrate our approach on an artificial symbolic regression benchmark where the parts of the formula are already known. Experimental results reveal how solutions are assembled within GP and explain diversity loss in GP populations through the proliferation of repeated patterns.",

author = "Bogdan Burlacu and Michael Affenzeller and Michael Kommenda and Gabriel Kronberger and Winkler, {Stephan M.}",

year = "2017",

language = "English",

editor = "{R. Moreno-Diaz, F.R. Pichler, A. Quesada-Arencibia}",

booktitle = "Lecture Notes in Computer Science",

}

TY - CHAP

T1 - Analysis of Schema Frequencies in Genetic Programming

AU - Burlacu, Bogdan

AU - Affenzeller, Michael

AU - Kommenda, Michael

AU - Kronberger, Gabriel

AU - Winkler, Stephan M.

PY - 2017

Y1 - 2017

N2 - Genetic Programming (GP) schemas are structural templates equivalent to hyperplanes in the search space. Schema theories provide information about the properties of subsets of the population and the behavior of genetic operators. In this paper we propose a practical methodology to identify relevant schemas and measure their frequency in the population. We demonstrate our approach on an artificial symbolic regression benchmark where the parts of the formula are already known. Experimental results reveal how solutions are assembled within GP and explain diversity loss in GP populations through the proliferation of repeated patterns.

AB - Genetic Programming (GP) schemas are structural templates equivalent to hyperplanes in the search space. Schema theories provide information about the properties of subsets of the population and the behavior of genetic operators. In this paper we propose a practical methodology to identify relevant schemas and measure their frequency in the population. We demonstrate our approach on an artificial symbolic regression benchmark where the parts of the formula are already known. Experimental results reveal how solutions are assembled within GP and explain diversity loss in GP populations through the proliferation of repeated patterns.

M3 - Chapter

BT - Lecture Notes in Computer Science

A2 - R. Moreno-Diaz, F.R. Pichler, A. Quesada-Arencibia, null

ER -