Design of the SNNS Neural Network Simulator

  • Andreas Zell
  • Niels Mache
  • Tilman Sommer
  • Thomas Korb
Part of the Informatik-Fachberichte book series (INFORMATIK, volume 287)


SNNS is a neural network simulator for Unix workstations developed at the Universität Stuttgart. It is a tool to generate, train, test and visualize artificial neural networks. The simulator consists of a simulator kernel, a graphical user interface based on X-Windows to interactively construct and visualize neural networks, and a compiler to generate large neural networks from a high level network description language. Applications of SNNS currently include printed character recognition, handwritten character recognition, recognition of machine parts, stock prize prediction, noise reduction in a telecom environment and texture analysis, among others. We also give preliminary design decisions for a planned parallel version of SNNS on a massively parallel SIMD-computer with more than 16,000 processors (MasPar MP-1216) which has been installed at our research institute recently.


Connectionism neural networks network simulators network description language 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [Carpenter, Grossberg 88]
    Carpenter, G.A., Grossberg, S.: The ART of Adaptive Pattern Recognition by a Self-Organizing Neural Network, IEEE Computer, March 1988, pp. 77–88Google Scholar
  2. [Chinn et al. 90]
    G. Chinn, K.A. Grajski, C. Chen, C. Kuszmaul, S. Tomboulian: Systolic Array Implementations of Neural Nets on the Mas Par MP-1 Massively Parallel Processor, Mas Par Corp. Int. ReportGoogle Scholar
  3. [Eckmiller 90]
    R. Eckmiller (Ed.): Advanced Neural Computers, North Holland, 1990Google Scholar
  4. [Eckmiller et al. 90]
    R. Eckmiller, G. Hartmann, G. Hauske (Ed.): Parallel Processing in Neural Systems and Computers, North Holland, 1990zbMATHGoogle Scholar
  5. [Goddard et al. 89]
    Goddard, N.H., Lynne, K.J., Mintz, T., Bukys, L.: The Rochester Connectionist Simulator: User Manual, Tech Report 233 (revised), Univ. of Rochester, NY, 1989Google Scholar
  6. [Grajski et al. 90]
    K.A. Grajski, G. Chinn, C. Chen, C. Kuszmaul, S. Tomboulian: Neural Network Simulation on the Mas Par MP-1 Massively Parallel Processor, Internat. Neural Network Conference, Paris, France, 1990Google Scholar
  7. [Hecht-Nielsen 88]
    Hecht-Nielsen, R.: Neurocomputing, Addison-Wesley, 1990Google Scholar
  8. [Hinton 89]
    Hinton, G.E.: Connectionist Learning Procedures, Artificial Intelligence 40(1989), p. 185–234CrossRefGoogle Scholar
  9. [NeuralWorks 90a, b, c]
    NeuralWorks Professional II: Neural Computing, Users Guide, Reference Guide, NeuralWare Inc., 1990Google Scholar
  10. [McClelland, Rumelhart 87]
    McClelland, J. A., Rumelhart, D.E., the PDP Research Group: Explorations in Parallel Distributed Processing, MIT Press, Cambridge MA, 1987Google Scholar
  11. [Mesrobian 89]
    E. Mesrobian, M. Stilber, J. Skrzypek: UCLA SFINX: Structure and Function in Neural Networks, Report No. UCLA-MPL-TR 89–8, Comp. Science Dept., UCLA, 1989Google Scholar
  12. [Pygmalion 90a]
    M. Hewetson: Pygmalion Neurocomputing, Graphic Monitor Tutorial v 1.1 & Graphic Monitor Manual, Dept. Comp. Science, University College, LondonGoogle Scholar
  13. [Pygmalion 90b]
    J. Taylor: Pygmalion Neurocomputing, Algorithm Library v 1.0, dittoGoogle Scholar
  14. [Pygmalion 90c]
    M. B. R. Vellasco: Pygmalion Neurocomputing, nC Tutorial & nC Manual v 1.02, dittoGoogle Scholar
  15. [Recce, Treleaven 89]
    Recce, M., Treleaven, P.C.: Parallel Architectures for Neural Computers, Neural Computers, Springer, 1989, pp. 487–495Google Scholar
  16. [Rumelhart, McClelland 86]
    Rumelhart, D.E., McClelland, J.A., the PDP Research Group: Parallel Distributed Processing, Vol. 1, 2, MIT Press, Cambridge MA, 1986Google Scholar
  17. [Singer 90]
    A. Singer: Implementations of Artificial Neural Networks on the Connection Machine, Thinking Machines Corp. Tech. Rep. RL 90–2, Jan. 1990 (also to appear in Parallel Computing, summer 1990)Google Scholar
  18. [SNNS 91a]
    A. Zell, Th. Korb, N. Mache, T. Sommer: SNNS, Stuttgarter Neuronale Netze Simulator, Benutzerhandbuch, Universität Stuttgart, Fakultät Informatik, Bericht Nr. 1/91, (in German)Google Scholar
  19. [SNNS 91b]
    A. Zell, Th. Korb, N. Mache, T. Sommer: SNNS, Stuttgarter Neuronale Netze Simulator, Nessus-Handbuch, Universität Stuttgart, Fakultät Informatik, Bericht Nr. 3/91, (in German)Google Scholar
  20. [Touretzky 89]
    Touretzky, D.: Advances in Neural Information Processing Systems 1, Morgan Kaufmann, 1989Google Scholar
  21. [Touretzky et al. 88]
    Touretzky, D., Hinton, G., Sejnowski, T.: Proc. of the 1988 Connectonist Models Stimmer School, June 17–26, Carnegie Mellon University, Morgan Kaufmann, 1988Google Scholar
  22. [Zhang et al. 89]
    X. Zhang, M. Mckenna, J.P. Mesirov, D. L. Waltz: An efficient implementation of the Back-propagation algorithm on the Connection Machine CM-2, Thinking Machines Corp. TRGoogle Scholar
  23. [Zell et al. 89]
    A. Zell, Th. Korb, T. Sommer, R. Bayer: NetSim, ein Simulator für Neuronale Netze, Informatik Fachberichte 216, D. Metzing (Hrsgb.) GWAI-89, 13th German Workshop on Artificial Intelligence, Eringerfeld, Sept. 89, Springer, pp. 134–143 (in German)Google Scholar
  24. [Zell et al. 90]
    A. Zell, Th. Korb, T. Sommer, R. Bayer: A Neural Network Simulation Environment, Proc. Applications of Neural Networks Conf., SPIE Vol. 1294, pp. 535–544Google Scholar
  25. [Zell et al. 91]
    A. Zell, Th. Korb, N. Mache, T. Sommer: Recent Developments of the SNNS Neural Network Simulator, Proc. Applications of Neural Networks Conf., SPIE Vol. 1294, 1991Google Scholar
  26. [Zipser, Rabin 86]
    D. Zipser, D.E. Rabin: P3: A Parallel Network Simulation System, in [Rumelhart, McClelland 86]Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1991

Authors and Affiliations

  • Andreas Zell
    • 1
  • Niels Mache
    • 1
  • Tilman Sommer
    • 1
  • Thomas Korb
    • 1
  1. 1.Institut für Parallele und Verteilte Höchstleistungsrechner (IPVR)Universität StuttgartStuttgart 80Deutschland

Personalised recommendations