Automatic feature selection in neuroevolution

  • Authors:

  • Shimon Whiteson;Peter Stone;Kenneth O. Stanley;Risto Miikkulainen;Nate Kohl

  • Affiliations:

  • University of Texas at Austin, Austin, TX;University of Texas at Austin, Austin, TX;University of Texas at Austin, Austin, TX;University of Texas at Austin, Austin, TX;University of Texas at Austin, Austin, TX

  • Venue:
  • GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation
  • Year:
  • 2005

Quantified Score

Hi-index 0.01

Visualization

Abstract

Feature selection is the process of finding the set of inputs to a machine learning algorithm that will yield the best performance. Developing a way to solve this problem automatically would make current machine learning methods much more useful. Previous efforts to automate feature selection rely on expensive meta-learning or are applicable only when labeled training data is available. This paper presents a novel method called FS-NEAT which extends the NEAT neuroevolution method to automatically determine an appropriate set of inputs for the networks it evolves. By learning the network's inputs, topology, and weights simultaneously, FS-NEAT addresses the feature selection problem without relying on meta-learning or labeled data. Initial experiments in an autonomous car racing simulation demonstrate that FS-NEAT can learn better and faster than regular NEAT. In addition, the networks it evolves are smaller and require fewer inputs. Furthermore, FS-NEAT's performance remains robust even as the feature selection task it faces is made increasingly difficult.