Evolutionary Intelligence

, Volume 1, Issue 1, pp 47–62

Neuroevolution: from architectures to learning

Review Article

DOI: 10.1007/s12065-007-0002-4

Cite this article as:
Floreano, D., Dürr, P. & Mattiussi, C. Evol. Intel. (2008) 1: 47. doi:10.1007/s12065-007-0002-4

Abstract

Artificial neural networks (ANNs) are applied to many real-world problems, ranging from pattern classification to robot control. In order to design a neural network for a particular task, the choice of an architecture (including the choice of a neuron model), and the choice of a learning algorithm have to be addressed. Evolutionary search methods can provide an automatic solution to these problems. New insights in both neuroscience and evolutionary biology have led to the development of increasingly powerful neuroevolution techniques over the last decade. This paper gives an overview of the most prominent methods for evolving ANNs with a special focus on recent advances in the synthesis of learning architectures.

Keywords

Neural networksEvolutionLearning

Copyright information

© Springer-Verlag 2008

Authors and Affiliations

  • Dario Floreano
    • 1
  • Peter Dürr
    • 1
  • Claudio Mattiussi
    • 1
  1. 1.Ecole Polytechnique Fédérale de Lausanne Laboratory of Intelligent SystemsLausanneSwitzerland