Evolutionary Intelligence

, Volume 1, Issue 4, pp 271–292

Automated feature selection in neuroevolution

  • Maxine Tan
  • Michael Hartley
  • Michel Bister
  • Rudi Deklerck
Research Paper

DOI: 10.1007/s12065-009-0018-z

Cite this article as:
Tan, M., Hartley, M., Bister, M. et al. Evol. Intel. (2009) 1: 271. doi:10.1007/s12065-009-0018-z

Abstract

Feature selection is a task of great importance. Many feature selection methods have been proposed, and can be divided generally into two groups based on their dependence on the learning algorithm/classifier. Recently, a feature selection method that selects features at the same time as it evolves neural networks that use those features as inputs called Feature Selective NeuroEvolution of Augmenting Topologies (FS-NEAT) was proposed by Whiteson et al. In this paper, a novel feature selection method called Feature Deselective NeuroEvolution of Augmenting Topologies (FD-NEAT) is presented. FD-NEAT begins with fully connected inputs in its networks, and drops irrelevant or redundant inputs as evolution progresses. Herein, the performances of FD-NEAT, FS-NEAT and traditional NEAT are compared in some mathematical problems, and in a challenging race car simulator domain (RARS). On the whole, the results show that FD-NEAT significantly outperforms FS-NEAT in terms of network performance and feature selection, and evolves networks that offer the best compromise between network size and performance.

Keywords

Neural networks Genetic algorithms Evolution Learning 

Copyright information

© Springer-Verlag 2009

Authors and Affiliations

  • Maxine Tan
    • 1
  • Michael Hartley
    • 2
  • Michel Bister
    • 1
  • Rudi Deklerck
    • 1
  1. 1.Department of Electronics and Informatics (ETRO)Vrije Universiteit Brussel, IBBTBrusselBelgium
  2. 2.DownUnder GeosolutionsSubiacoAustralia

Personalised recommendations