A General Framework for Encoding and Evolving Neural Networks

  • Authors:

  • Yohannes Kassahun;Jan Hendrik Metzen;Jose Gea;Mark Edgington;Frank Kirchner

  • Affiliations:

  • Robotics Group, University of Bremen, Robert-Hooke-Str. 5, D-28359, Bremen, Germany;Robotics Group, University of Bremen, Robert-Hooke-Str. 5, D-28359, Bremen, Germany;Robotics Group, University of Bremen, Robert-Hooke-Str. 5, D-28359, Bremen, Germany;Robotics Group, University of Bremen, Robert-Hooke-Str. 5, D-28359, Bremen, Germany;Robotics Group, University of Bremen, Robert-Hooke-Str. 5, D-28359, Bremen, Germany and German Research Center for Artificial Intelligence (DFKI), Robert-Hooke-Str. 5, D-28359, Bremen, Germany

  • Venue:
  • KI '07 Proceedings of the 30th annual German conference on Advances in Artificial Intelligence
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper we present a novel general framework for encoding and evolving networks called Common Genetic Encoding (CGE) that can be applied to both direct and indirect encoding methods. The encoding has important properties that makes it suitable for evolving neural networks: (1) It is completein that it is able to represent all types of valid phenotype networks. (2) It is closed, i. e. every valid genotype represents a valid phenotype. Similarly, the encoding is closed under genetic operatorssuch as structural mutation and crossover that act upon the genotype. Moreover, the encoding's genotype can be seen as a composition of several subgenomes, which makes it to inherently support the evolution of modular networks in both direct and indirect encoding cases. To demonstrate our encoding, we present an experiment where direct encoding is used to learn the dynamic model of a two-link arm robot. We also provide an illustration of how the indirect-encoding features of CGE can be used in the area of artificial embryogeny.