From the Chromosome to the Neural Network

  • Olivier Michel
  • Joëlle Biondi


A proposal for a model of morphogenesis process taking inspiration from biology is presented in this paper. This process uses a chromosome as a production system to create an artificial neural network. It starts with a single cell containing the chromosome. Cells can divide and establish connections among them. Both structure and weights of the neural network are defined by the morphogenesis process. An application to a neural network driving an autonomous mobile robot is presented which exhibits encouraging first results.


Neural Network Genetic Algorithm Real Robot Autonomous Mobile Robot Linear Chromosome 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    E.J.W. Boers and H. Kuiper. Biological metaphors and the design of modular artificial neural networks. PhD thesis, Departments of Computer Science and Experimental Psychology at Leiden University, The Netherlands, 1992.Google Scholar
  2. [2]
    V. Braitenberg. Vehicles: Experiments in Synthetic Psychology. MIT Press, Cambridge, 1984.Google Scholar
  3. [3]
    Dave Cliff, Inman Harvey, and Phil Husband. Explorations in evolutionary robotics. Adaptive Behavior, 2 (1): 73–110, 1993.CrossRefGoogle Scholar
  4. [4]
    B. Fullmer and R. Miikkulainen. Using marker- based genetic encoding of neural networks to evolve finite-state behaviour. In F. Varela and P. Bourgine, editors, Towards a Practice of Autonomous Systems, Proceedings of the First Inter-national Conference on Artificial Life, Paris. MIT Press, 1992.Google Scholar
  5. [5]
    D.E. Goldberg. Genetic Algorithms in Search, Op-timisation and Machine Learning. Addison Wesley, Massachussets, 1989.Google Scholar
  6. [6]
    F. Gruau and D. Whitley. The cellular developmental of neural networks: the interaction of learning and evolution. Technical report, Ecole Normale Superieure de Lyon, 46, Allee d’ltalie, 69364 Lyon Cedex 07, France, January 1993.Google Scholar
  7. [7]
    S. Harp and T. Samad. Genetic synthesis of neural network architecture. In Lawrence Davis, editor, Handbook of Genetic Algorithms, chapter 15, pages 202–221. Van Nostrand Reinhold, 1991.Google Scholar
  8. [8]
    Inman Harvey. Species adaptation genetic algorithms: A basis for a continuing saga. In F. Varela and P. Bourgine, editors, Towards a Practice of Autonomous Systems, Proceedings of the First International Conference on Artificial Life, Paris, pages 346–354. MIT Press, 1992.Google Scholar
  9. [9]
    T. Kohonen. Self-Organization and Associative Memory. Springer-Verlag, 1989. (3rd ed.).Google Scholar
  10. [10]
    Y. Le Cun, B. Boser, J.S. Denker, D. Henderson, R.E. Howard, W. Hubbard, and L.D. Jackel. Handwritten digit recognition with a back- propagation network. In D.S. Touretzky, editor, Advances in Neural Information Processing Sys-tems II. Morgan Kaufmann, 1990.Google Scholar
  11. [11]
    G.F. Miller, P.M. Todd, and S.U. Hegde. Designing neural networks using genetic algorithms. In Schaffer J.D., editor, Proceeding of the Third International Conference on Genetic Algorithms, pages 379–384. Morgan Kaufmann, 1989.Google Scholar
  12. [12]
    F. Mondada, E. Franzi, and P. Ienne. Mobile robot miniaturisation: A tool for investigation in control algorithms. In Third International Symposium on Experimental Robotics, Kyoto, Japan, October 1993.Google Scholar
  13. [13]
    F. Mondada and C. Touzet. Quelques comportements adaptatifs pour le robot miniature khepera. In Annales du Groupe CARNAC% EPFL, Lausanne Suisse, 1993.Google Scholar
  14. [14]
    J.F. Varela. Autonomie et Connaissance. Editions du Seuil, Paris, Janvier 1989.Google Scholar

Copyright information

© Springer-Verlag/Wien 1995

Authors and Affiliations

  • Olivier Michel
    • 1
  • Joëlle Biondi
    • 1
  1. 1.Laboratory I3SCNRS-UNSAFrance

Personalised recommendations