NNDT — A Neural Network Development Tool

  • Björn Saxén
  • Henrik Saxén


A tool for analysis, modelling, simulation and prediction with feedforward and recurrent neural networks is presented. The Neural Network Development Tool (NNDT) is implemented in Visual Basic and C and runs under MS Windows on personal computers. Network training is carried out by the Levenberg-Marquardt method and the user interface facilitates interactive analysis and modification of parameters as well as illustration of results. The features offered by the tool are especially useful in the difficult process of training recurrent networks, but are also of value, e.g., in scanning the performance of feedforward networks for analysing if and when overfitting occurs.


Hide Node Recurrent Neural Network Feedforward Network Recurrent Network Feedback Connection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Demuth, H. and M. Beale, Neural Network ToolBox for use with MATLAB, The MathWorks Inc., 1993.Google Scholar
  2. [2]
    Tsung, F-S., Modeling Dynamical Systems with Recurrent Networks, Ph.D. Dissertation, University of California, San Diego 1994.Google Scholar
  3. [3]
    IEEE Transactions on Neural Networks (Special Issue on Dynamic Recurrent Neural Networks) 5, No. 4,1994.Google Scholar
  4. [4]
    Rumelhart, D. E. and J. McClelland (Eds.), Parallel Distributed Processing, MIT Press, 1986.Google Scholar
  5. [5]
    Bulsari, A. B. and H. Saxén, Neurocomputing 7, 29–40, 1995.MATHCrossRefGoogle Scholar
  6. [6]
    Press, W. H., B. P. Flannery, S. A. Teukolsky, and W. T. Vetterling, Numerical Recipes, Cambridge University Press, Cambridge 1986.Google Scholar
  7. [7]
    Marquardt, D. W., J. SIAM 11, 431–441, 1963.MathSciNetMATHGoogle Scholar
  8. [8]
    Williams, R. J. and D. Zipser, Neural Computation 1, 270–280, 1989.CrossRefGoogle Scholar
  9. [9]
    Jordan, M. I., Proceedings of the Eight Annual Conference of the Cognitive Science Society, Amherst, 531–546, Hillsdale: Erlbaum 1986.Google Scholar
  10. [10]
    Bulsari, A. B. and H. Saxén, Proceedings of International Conference on Neural Networks and Genetic Algorithms (ICANNGA’93) Innsbruck, Austria, (Eds. R. F. Albrecht), 285–291, Springer-Verlag, Wien 1993.Google Scholar
  11. [11]
    Bulsari, A. and H. Saxén, Proceedings of the International Joint Conference on Neural Networks (IJCNN’93-Nagoya), Nagoya, Japan, October 1993, Vol. 1, 995–998.Google Scholar
  12. [12]
    Weigend, A. S., B. A. Huberman and D. E. Rumelhart, International Journal of Neural Systems 1, 193–209, 1990.CrossRefGoogle Scholar
  13. [13]
    Finnoff, W., F. Hegert and H. G. Zimmermann, Neural Networks 6, 771–783, 1993.CrossRefGoogle Scholar
  14. [14]
    Ljung, L. and J. Sjöberg, Neural Networks for Signal Processing II (eds. S. Y. Kuhn, et al.), 423–435, IEEE 1992.CrossRefGoogle Scholar
  15. [15]
    Tong, H, Non-linear Time Series, Oxford University Press, Oxford, 1990.MATHGoogle Scholar

Copyright information

© Springer-Verlag/Wien 1995

Authors and Affiliations

  • Björn Saxén
    • 1
  • Henrik Saxén
    • 1
  1. 1.Heat Engineering Laboratory, Department of Chemical EngineeringÅbo Akademi UniversityÅboFinland

Personalised recommendations