The NeuDB-system: Towards the integration of neural networks and database systems

  • Erich Schikuta
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 861)


In this paper the NeuDB system is presented, which accomplishes the physical and conceptual integration of neural networks with an object-oriented database system. In the context of the database system neural networks are seen as basic objects and are administrated via the conventional and handy interface of the system. The network paradigm of a neural network object is defined by the respective sub type according to the type hierarchy of the general neural net database type. The structural information is stored using a data oriented approach. The dynamic components of the neural networks are triggered by conventional database operations (insertion, update, etc.) and are processed by an independent neural network server.

Overall a conceptual framework for the embedding of neural networks into database systems and an embedding classification is given.


Neural networks database systems object-orientation integrational aspects data modeling 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Parsaye K., Chignell M., Khoshafian S., Wong H, Intelligent data base and automatic discovery, In Neural and Intelligent Systems Integration, (ed. B. Soucek), John Wiley Inc., pp. 615–629, 1991Google Scholar
  2. 2.
    Heileman G., et al., A general framework for concurrent simulation of neural networks models, IEEE Trans. Software Engineering, 18, 7, pp. 551–562, 1992Google Scholar
  3. 3.
    Schikuta E., The role of neural networks in knowledge based systems, Proc. Int. Symp. on nonlinear theory and applications, Hawaii, 1993Google Scholar
  4. 4.
    Pao Y.-H., Sobajic D.J., Neural networks and Knowledge Engineering, IEEE Knowledge and Data Engineering, 3, 2, pp. 185–192, June 1991Google Scholar
  5. 5.
    Leighton R., The Aspirin/MIGRAINES Neural Network Software, user manual, MITRE Corp., 1992Google Scholar
  6. 6.
    SOM Prog. Team, SOM-PAK, The Self-Organizing Map Program Package, user guide, Helsinki, 1992Google Scholar
  7. 7.
    Hecht-Nielsen R., Neurocomputing, Addison/Wesley, 1989Google Scholar
  8. 8.
    Zell A. et al., SNNS, Stuttgart Neural Network Simulator, User Manual, Tech.Rep.No. 3/92, Univ. Stuttgart, 1992Google Scholar
  9. 9.
    Camp D.v., Xerion Neural Network Simulator, user guide, Univ. Toronto, 1992Google Scholar
  10. 10.
    Wecker D.B., The Neural Design and Simulation System (NeurDS), Digital Tech. Rep. 589, May 1989Google Scholar
  11. 11.
    Stonebraker M., et. al., Extending a Database system with Procedures, ACM Transactions on Database Systems, Sept. 1987Google Scholar
  12. 12.
    Rowe L., Stonebraker M., The POSTGRES data model, Proc. 1987 Conference on Very Large Database Systems, Brighton, 1987Google Scholar
  13. 13.
    Beale R., Neural Computing: an introduction, Hilger, 1990Google Scholar
  14. 14.
    Rumelhardt, D.E. et al., Learning internal Representation by Error Propagation, in Rumelhardt D.E. et al., Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol 1, MIT Press, 1986Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1994

Authors and Affiliations

  • Erich Schikuta
    • 1
  1. 1.Institute of Applied Computer Science and Information Systems, Dept. of Data EngineeringUniversity of ViennaViennaAustria

Personalised recommendations