Universal Spike-Train Processor for a High-Speed Simulation of Pulsed Para-neural Networks

  • Michal Joachimczak
  • Beata Grzyb
  • Daniel Jelinski
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3316)

Abstract

We propose a Universal Spiketrain Processor (USP) – a computing device for high-speed execution of Pulsed Para-Neural Networks (PPNN). PPNN is a graph consisting of processing nodes and directed edges, called axons. We provide a description of USP architecture, a USP-specific language of PPNN coding, and methods of conversion of the already existing PPNN code into a USP code. We also compare the USP’s performance with the already existing cellular-automata-based tools for PPNN simulation.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Buller: CAM-Brain Machines and Pulsed Para-Neural Networks (PPNN): Toward a hardware for future robotic on-board brains. In: Proceedings, 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, H.E., 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
  3. 3.
    Buller, H., Hemmi, M., Joachimczak, J., Liu, K., Shimohara, K., Stefanski, A.: ATR Artificial Brain Project: Key Assumptions and Current State. In: Proceedings, 9th International Symposium on Artificial Life and Robotics (AROB 9th 2004), Beppu, Japan, January 28-30 (2004)Google Scholar
  4. 4.
    Buller, Tuli, T.S.: Four-legged robot.s behavior controlled by Pulsed para-neural net orks (PPNN). In: Proceedings, 9th International Conference on Neural Information Processing (ICONIP 2002), Singapore, November 18-22, vol. 1, pp. 239–242 (2002)Google Scholar
  5. 5.
    Joachimczak, M., Buller, A.: Universal Spiketrain Processor. ATR HIS, Kyoto (2003); Unpublished reseach memoGoogle Scholar
  6. 6.
    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.Google Scholar
  7. 7.
    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
  8. 8.
    Jelinski, D., Joachimczak, M.: Heuristic-based Computer-Aided Synthesis of Spatial β-type Pulsed Para-Neural networks (3D-β PPNNs), Proceedings, 8th International Symposium. In: On Artificial Life and Robotics (AROB 8th 2003), Beppu, Japan, January 24-26, pp. 499–501 (2003)Google Scholar
  9. 9.
    Buller, A., Joachimczak, M., Liu, J., Stefanski, A.: Neuromazes: 3-Dimensional Spiketrain Processors. WSEAS Transactions on Computers 3(1), 157–161 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Michal Joachimczak
    • 1
  • Beata Grzyb
    • 2
  • Daniel Jelinski
    • 1
  1. 1.Dept. of Electronics, Telecommunications and InformaticsTechnical University of GdanskGdanskPoland
  2. 2.Faculty of Mathematics, Physics and Computer Sci.Maria Curie-SklodowskaUniversityin LublinLublinPoland

Personalised recommendations