Fitness Landscapes and Inductive Genetic Programming

Slavov, V.; Nikolaev, Nikolay

doi:10.1007/978-3-7091-6492-1_91

Cited by 11 publications

(9 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It allows for a more theoretical exploration that is complementary to the prevailing empirical evaluation of EAs for decision tree induction. Examples of works that make use of such a methodology are [39], [48], [54], [64], [73], [145]. In [145], for example, instances were artificially generated in order to produce data sets with specific characteristics, such as representative enough categorical distributions and extreme cases of easiness or hardness for decision tree induction.…”

Section: What Is Next On Evolutionary Induction Of Decision Trees?mentioning

confidence: 99%

A Survey of Evolutionary Algorithms for Decision-Tree Induction

Barros

Basgalupp

Carvalho

et al. 2012

IEEE Trans. Syst., Man, Cybern. C

298

139

View full text Add to dashboard Cite

Abstract-This paper presents a survey of evolutionary algorithms designed for decision tree induction. In this context, most of the paper focuses on approaches that evolve decision trees as an alternate heuristics to the traditional top-down divideand-conquer approach. Additionally, we present some alternative methods that make use of evolutionary algorithms to improve particular components of decision tree classifiers. The paper original contributions are the following. First, it provides an upto-date overview that is fully focused on evolutionary algorithms and decision trees and does not concentrate on any specific evolutionary approach. Second, it provides a taxonomy which addresses works that evolve decision trees and works that design decision tree components using evolutionary algorithms. Finally, a number of references is provided that describe applications of evolutionary algorithms for decision tree induction in different domains. The paper ends by addressing some important issues and open questions that can be subject of future research.

show abstract

Section: What Is Next On Evolutionary Induction Of Decision Trees?mentioning

confidence: 99%

A Survey of Evolutionary Algorithms for Decision-Tree Induction

Barros

Basgalupp

Carvalho

et al. 2012

IEEE Trans. Syst., Man, Cybern. C

298

139

View full text Add to dashboard Cite

show abstract

“…There are some initial works that have attempted calculating the distance between a pair of trees [11,16]. However, these works were limited in the sense that they did not offer a reliable distance.…”

Section: Fitness Distance Correlationmentioning

confidence: 99%

An Empirical Investigation of How Degree Neutrality Affects GP Search

Galván

Poli

2009

MICAI 2009: Advances in Artificial Intelligence

View full text Add to dashboard Cite

Abstract. Over the last years, neutrality has inspired many researchers in the area of Evolutionary Computation (EC) systems in the hope that it can aid evolution. However, there are contradictory results on the effects of neutrality in evolutionary search. The aim of this paper is to understand how neutralitynamed in this paper degree neutrality -affects GP search. For analysis purposes, we use a well-defined measure of hardness (i.e., fitness distance correlation) as an indicator of difficulty in the absence and in the presence of neutrality, we propose a novel approach to normalise distances between a pair of trees and finally, we use a problem with deceptive features where GP is well-known to have poor performance and see the effects of neutrality in GP search.

show abstract

“…That is why, we modify the measure so that the relative frequencies of the examples are computed with the following conditional probabilities [9]:…”

Section: F( Dt) = Min{ I( Dt) § I(eldt) } I(dt) = Nf + Nl + Nf • Log2mentioning

confidence: 99%

“…The approach is illustrated with elaboration of a fitness function for efficient concept learning by inductive Genetic Programming with Decision Trees (GPDT) [9]. The claim is that a careful design of a stochastic complexity fitness function helps to achieve: first, mitigating the navigation difficulties by increasing the global landscape correlatation, and, second, keeping a balance between the parsimony and accuracy of the decision trees.…”

Section: Introductionmentioning

confidence: 99%

Inductive Genetic Programming with Decision Trees

Nikolaev

Slavov

1997

Machine Learning: ECML-97

View full text Add to dashboard Cite

Abstract. This paper proposes an empirical study of inductive Genetic Programming with Decision Trees. An approach to development of fitness functions for efficient navigation of the search process is presented. It relies on analysis of the fitness landscape structure and suggests measuring its characteristics with statistical correlations. We demonstrate that this approach increases the global landscape correlation, and thus leads to mitigation of the search difficulties. Another claim is that the elaborated fitness functions help to produce decision trees with low syntactic complexity and high predictive accuracy.

show abstract

Fitness Landscapes and Inductive Genetic Programming

Cited by 11 publications

References 2 publications

A Survey of Evolutionary Algorithms for Decision-Tree Induction

A Survey of Evolutionary Algorithms for Decision-Tree Induction

An Empirical Investigation of How Degree Neutrality Affects GP Search

Inductive Genetic Programming with Decision Trees

Contact Info

Product

Resources

About