CONTEXT 2003: Modeling and Using Context pp 435-442 | Cite as

Contextual Modeling Using Context-Dependent Feedforward Neural Nets

  • Piotr Ciskowski
Conference paper
First Online:
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2680)

Abstract

The paper addresses the problem of using contextual information by neural nets solving problems of contextual nature. The models of a context-dependent neuron and a multi-layer net are recalled and supplemented by the analysis of context-dependent and hybrid nets’ architecture. The context-dependent nets’ properties are discussed and compared with the properties of traditional nets considering the Vapnik-Chervonenkis dimension, contextual classification and solving tasks of contextual nature. The possibilities of applications to classification and control problems are also outlined.

This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    M. Anthony and P. Bartlett. Neural Network Learning: Theoretical Foundations. Cambridge University Press.Google Scholar
  2. 2.
    P. Ciskowski. Vapnik-chervonenkis dimension of a context-dependent perceptron. In Proc. Third International and Interdisciplinary Conference on Modeling and Using Context, CONTEXT 2001, Dundee, UK, 2001.Google Scholar
  3. 3.
    P. Ciskowski. Learning of context-dependent neural nets. PhD thesis, Wroclaw University of Technology, 2002.Google Scholar
  4. 4.
    E. Rafajlowicz. Context-dependent neural nets — problem statement and examples. In Proc. Third Conference Neural Networks and Their Applications, Zakopane, Poland, May 1999.Google Scholar
  5. 5.
    B. Spencer Jr., S. Dyke, S. M., and J. Carlson. Phenomenological model for magnetorheological dampers. Computer of Engineering mechanics, ASCE, 123(3):230–238, 1997.CrossRefGoogle Scholar
  6. 6.
    R. Watrous and G. Towell. A patient-adaptive neural network ECG patient monitoring algorithm. In Computer in Cardiology, Vienna, Austria, September 10–13 1995.Google Scholar
  7. 7.
    D. Yeung and G. Bekey. Using a context-sensitive learning for robot arm control. In Proc. IEEE International Conference on Robotics and Automation, pages 1441–1447, Scottsdale, Arizona, May 14–19 1989.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Piotr Ciskowski
    • 1
  1. 1.Institute of Engineering CyberneticsWrocław University of TechnologyWrocławPoland

Personalised recommendations