Advertisement

CAM-Brain: A new model for atr's cellular automata based artificial brain project

  • Felix Gers
  • Hugo de Garis
Evolvable Hardware
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1259)

Abstract

This paper introduces a new model for ATR's CAM-Brain Project, which is far more efficient and simpler than the older model. The CAM-Brain Project aims at building a billion neuron artificial brain using “evolutionary engineering” technologies. Our neural structures are based on Cellular Automata (CA) and grow/evolve in special hardware such as MIT's “CAM-8” machine. With the CAM-8 and the new CAM-Brain model, it is possible to grow a neural structure with several million neurons in a 128 M cell CA-space, at a speed of 200 M cell-updates per second. The improvements in the new model are based on a new CA-implementation technique, on reducing the number of cell-behaviors to two, and on using genetic encoding of neural structures in which the chromosome is initially distributed homogeneously over the entire CA-space. This new CAM-Brain model allows the implementation of neural structures directly in parallel hardware, evolving at hardware speeds.

Keywords

Artificial Brains Evolutionary Engineering Neural Networks Genetic Algorithms Genetic Encoding Cellular Automata Cellular Automata Machine (CAM-8) Evolvable Hardware 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Toffoli, T. & Margolous, N.’ Cellular Automata Machines', MIT Press, Cambridge, MA, 1987.Google Scholar
  2. 2.
    von Neumann, J.’ Theory of Self-Reproducing Automata', ed. Burks A.W. University of Illinois Press, Urbana, 1966Google Scholar
  3. 3.
    Codd, E.F.’ Cellular Automata', Academic Press, NY 1968.Google Scholar
  4. 4.
    de Garis, H.’ CAM-BRAIN: The Evolutionary Engineering of a Billion Neuron Artificial Brain by 2001 which Grows/Evolves at Electronic Speed Inside a Cellular Automata Machine (CAM)', in’ Towards Evolvable Hardware', Springer, Berlin, Heidelberg, NY, 1996.Google Scholar
  5. 5.
    Lloyd, S.’ A Potentially Realizable Quantum Computer', Science 261, 1569–1571 1993.Google Scholar
  6. 6.
    Koza, J.R.’ Genetic Programming: On the Programming of Computers by the Means of Natural Selection', Cambrige, MA, MIT Press, 1992Google Scholar
  7. 7.
    Koza, J.R. & Bennet, F.H. & Andre, D. & Keane, M.M.’ Toward Evolution of Electronic Animals Using Genetic Programming', ALife V Conference Proceedings, MIT Press, 1996.Google Scholar
  8. 8.
    Sipper, M.’ Co-evolving Non-Uniform Cellular Automata to Perform Computations', Physica D 92, 193–208 1996.Google Scholar
  9. 9.
    Carter, F. L.’ Molecular Electronic Devices', North-Holland, Amsterdam, NY, Oxford, Tokyo, 1986.Google Scholar
  10. 10.
    Gers, F. A. & de Garis, H.’ Porting a Cellular Automata Based Artificial Brain to MIT's Cellular Automata Machine’ CAM-8”, (submitted).Google Scholar
  11. 11.
    Margolus, N.’ Crystalline Computation', (Preprint).Google Scholar
  12. 12.
    de Garis, H.’ One Chip Evolvable Hardware: 1C-EHW', (submitted).Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Felix Gers
    • 1
  • Hugo de Garis
    • 1
  1. 1.Human Information Processing LaboratoriesATRKyotoJapan

Personalised recommendations