Mining evolving learning algorithms

András Joó*

*Corresponding author for this work

Research output: Chapter in Book/Published conference outputConference publication

Abstract

This paper presents an empirical method to identify salient patterns in tree based Genetic Programming. By using an algorithm derived from tree mining techniques and measuring the destructiveness of replacing patterns, we are able to identify those patterns that are responsible for the increased fitness of good individuals. The method is demonstraded on the evolution of learning rules for binary perceptrons.

Original languageEnglish
Title of host publicationGenetic programming: 12th European Conference, EuroGP 2009 Tübingen, Germany, April 15-17, 2009 Proceedings
Place of PublicationBerlin (DE)
PublisherSpringer
Pages73-84
Number of pages12
ISBN (Electronic)978-3-642-01181-8
ISBN (Print)3-642-01180-2, 978-3-642-01180-1
DOIs
Publication statusPublished - 23 Jul 2009
Event12th European Conference on Genetic Programming, EuroGP 2009 - Tubingen, Germany
Duration: 15 Apr 200917 Apr 2009

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume5481
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference12th European Conference on Genetic Programming, EuroGP 2009
Country/TerritoryGermany
CityTubingen
Period15/04/0917/04/09

Keywords

  • genetic programming
  • learning rule
  • perceptron
  • tree mining

Fingerprint

Dive into the research topics of 'Mining evolving learning algorithms'. Together they form a unique fingerprint.

Cite this