Pulsed Para-neural Networks (PPNN) Based on MEXOR Logic

  • Andrzej Buller
  • Ismail Ahson
  • Muzaffar Azim
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3316)

Abstract

We present Pulsed Para-Neural Networks (PPNN) defined as graphs consisting of processing nodes and directed edges, called axons. We discuss PPNNs in which every node has up to 3 inputs and returns a pulse at clock t if itreceived one and only one pulse at clock t-1. Axons represent pure delays. We provide theoretical account for MEXOR Logic underlying the behavior of the presented PPNNs. A number of proven theorems and schemes of practical devices shows that MEXOR-based PPNNs may be considered as a step toward a future-generation evolvable hardware for a brain-like computing.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Buller, A.: CAM-Brain Machines and Pulsed Para-Neural Networks (PPNN): Toward a hardware for future robotic on-board brains. In: 8th International Symposium. on Artificial Life and Robotics (AROB 8th 2003), Beppu, Japan, January 24-26, pp. 490–493 (2003)Google Scholar
  2. 2.
    Buller, A., Hemmi, H., Joachimczak, M., Liu, J., Shimohara, K., Stefanski, A.: ATR Artificial Brain Project: Key Assumptions and Current State. In: 9th International Symposium on Artificial Life and Robotics (AROB 9th ), Japan, January 28-30, 2004, pp. 166–169 (2004)Google Scholar
  3. 3.
    Buller, A., Tuli, T.S.: Four-legged robot.s behavior controlled by Pulsed para-neural networks (PPNN). In: Proceedings, 9th International Conference on Neural Information Processing (ICONIP 2002), Singapore, November 18-22, vol. 1, pp. 239–242 (2002)Google Scholar
  4. 4.
    Buller, A., Eeckhaut, H., Joachimczak, M.: Pulsed para-neural network (PPNN) synthesis in a 3-D cellular automata space. In: Proceedings, 9th International Conference on Neural Information Processing (ICONIP 2002), Singapore, November 18-22, vol. 1, pp. 581–584 (2002)Google Scholar
  5. 5.
    Buller, A.: Neuromazes: 3-Dimensional Spiketrain Processors. WSEAS Transactions on Computers 3(1), 157–161 (2004)Google Scholar
  6. 6.
    Eeckhaut, H., Van Campenhout, J.: Handcrafting Pulsed Neural Networks for the CAMBrain Machine. In: 8th International Symposium on Artificial Life and Robotics (AROB 8th 2003), Beppu, Japan, January 24-26, pp. 494–498 (2003)Google Scholar
  7. 7.
    Gers, F., de Garis, H., Korkin, M.: CoDi-1Bit: A Simplified Cellular Automata based Neuron Model. In: Evolution Artificiele 1997, Nimes, France, October 22, pp. 211–229 (1997)Google Scholar
  8. 8.
    Hachtel, G.D., Somenzi, F.: Logic Synthesis and Verification Algorithms. Kluwer Academic Publ., Dordrecht (1996)Google Scholar
  9. 9.
    Hecht-Nielsen, R.: Neurocomputing. Addison-Wesley, Reading (1990)Google Scholar
  10. 10.
    Korkin, M., Fehr, G., Jeffrey, G.: Evolving hardware on a large scale. In: Proceedings the Second NASA / DoD Workshop on Evolvable Hardware, Pasadena, July 2000, pp. 173–181 (2000)Google Scholar
  11. 11.
    McCulloch, W.S., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bulletin of Math. Bio 5, 115–133 (1943)MATHCrossRefMathSciNetGoogle Scholar
  12. 12.
    Liu, J.: NeuroMazeTM. User.s Guide, Version 3.0. In: ATR Human Information Science Labs, Kyoto, Japan (2002)Google Scholar
  13. 13.
    Sasao, T.: Switching Theory for Logic Synthesis. Kluwer Academic Publ., Boston (1999)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Andrzej Buller
    • 1
  • Ismail Ahson
    • 2
  • Muzaffar Azim
    • 2
  1. 1.NIS Labs.Advanced Telecommunications Research Institute International (ATR)KyotoJapan
  2. 2.Jamia Millia UniversityOkhla, New DelhiIndia

Personalised recommendations