Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Symbolic regression for knowledge discovery: bloat, overfitting, and variable interaction networks

Symbolic regression for knowledge discovery: bloat, overfitting, and variable interaction networks EDITORIAL Freshly Printed Symbolic Regression for Knowledge Discovery Bloat, Over tting, and Variable Interaction Networks Dipl.-Ing. Dr. Gabriel Kronberger This work describes an approach for data analysis based on symbolic regression and genetic programming, that produces an overall view of the dependencies of all variables of a system. The identi ed dependencies are represented in form of a variable interaction network. In the rst part of this work, this approach is described in detail. Important issues are the prevention of bloat and over tting, the simpli cation of models, and the identi cation of relevant input variables. In this context, different methods for bloat control are presented and compared. In addition, a novel way to detect and reduce over tting is presented and analyzed. The second part of this work demonstrates how comprehensive symbolic regression can be applied for analysis of real-world systems. Variable interaction networks for a blast furnace process and an industrial chemical process are presented and discussed. Additionally, the same approach is also applied on an economic data set to identify macro-economic dependencies. Gabriel Kronberger: Symbolic Regressionfor Knowledge Discovery: Bloat, Over tting, and Vari- able Interaction Networks - 1. Edition 2011, 214 pages, A5, paperback, ISBN 978-3-85499-875-4 SIGEVOlution Volume 5, Issue 4 http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM SIGEVOlution Association for Computing Machinery

Symbolic regression for knowledge discovery: bloat, overfitting, and variable interaction networks

Kronberger, Gabriel
ACM SIGEVOlution , Volume 5 (4) – Nov 1, 2011
Download PDF
1 page

Loading next page...
 
/lp/association-for-computing-machinery/symbolic-regression-for-knowledge-discovery-bloat-overfitting-and-oFw2w3Ggww

References (6)

Publisher
Association for Computing Machinery
Copyright
Copyright © 2011 by ACM Inc.
ISSN
1931-8499
DOI
10.1145/2078245.2078249
Publisher site
See Article on Publisher Site

Abstract

EDITORIAL Freshly Printed Symbolic Regression for Knowledge Discovery Bloat, Over tting, and Variable Interaction Networks Dipl.-Ing. Dr. Gabriel Kronberger This work describes an approach for data analysis based on symbolic regression and genetic programming, that produces an overall view of the dependencies of all variables of a system. The identi ed dependencies are represented in form of a variable interaction network. In the rst part of this work, this approach is described in detail. Important issues are the prevention of bloat and over tting, the simpli cation of models, and the identi cation of relevant input variables. In this context, different methods for bloat control are presented and compared. In addition, a novel way to detect and reduce over tting is presented and analyzed. The second part of this work demonstrates how comprehensive symbolic regression can be applied for analysis of real-world systems. Variable interaction networks for a blast furnace process and an industrial chemical process are presented and discussed. Additionally, the same approach is also applied on an economic data set to identify macro-economic dependencies. Gabriel Kronberger: Symbolic Regressionfor Knowledge Discovery: Bloat, Over tting, and Vari- able Interaction Networks - 1. Edition 2011, 214 pages, A5, paperback, ISBN 978-3-85499-875-4 SIGEVOlution Volume 5, Issue 4

Journal

ACM SIGEVOlution – Association for Computing Machinery

Published: Nov 1, 2011

There are no references for this article.