Skip to main content

Pruning Neural Networks for a Two-Link Robot Control System

  • Conference paper
Computational Intelligence and Bioinspired Systems (IWANN 2005)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 3512))

Included in the following conference series:

  • 2558 Accesses

Abstract

Two-link robot arm model is extensively used in literatures for that it is simple enough to simulate conveniently, yet contains all the nonlinear terms arising in general n-link manipulators. And neural networks are reported to be computationally efficient compared with traditional PID control and adaptive control. However, when a neural network is applied, one of the key step is to choose the optimal number of neurons. In this paper, a relative large number of neurons are initially used, which is pruned during the training. The conic sector theory is introduced in the design of this robust neural control system, which aims at providing guaranteed boundedness for both the input-output(I/O) signals and the weights of the neural network.

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

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Song, Q., Xiao, J., Soh, Y.C.: Robust Backpropagation Training Algorithm for Multilayered Neural Tracking Controller. IEEE Transactions on Neural Networks 10, 1133–1141 (1999)

    Article  Google Scholar 

  2. Lee, M., choi, H.-S.: A Robust Neural controller for Underwater Robot Manipulators. IEEE Transactions on Neural Networks 11, 1465–1470 (2000)

    Article  Google Scholar 

  3. Jagannathan, S., Lewis, F.L.: Multilayer Discrete-Time Neural-Net Controller with Guaranteed Performance. IEEE Trans. On Neural Networks 7(1), 107–130 (1996)

    Article  Google Scholar 

  4. Jagannathan, S., Lewis, F.L.: Discrete-Time Neural Net Controller for a Class of Nonlinear Dynamic Systems. IEEE Trans. On Automatic Control 4(11), 1693–1699 (1996)

    Article  MathSciNet  Google Scholar 

  5. Spall, J.C.: Adaptive Stochastic Approximation by the Simultaneous Perturbation Method. IEEE Trans. On Automatic Control 45, 1839–1853 (2000)

    Article  MATH  MathSciNet  Google Scholar 

  6. Hassibi, B., Stork, D.G.: Second-order derivatives for network pruning: Optimal brain surgeon. Advances in Neural Information Processing Systems, 164–171 (1993)

    Google Scholar 

  7. Safanov, M.G.: Stability and robustness of multivariable feedback systems. MIT Press, Cambridge (1980)

    Google Scholar 

  8. Cluett, V.R., Shah, L., Fisher, G.: Robustness Analysis of Discrete-Time Adaptive Control Systems Using Input-Output Stability Theory: a Tutorial. IEE Proceedings, Part D 135, 133–141 (1988)

    MATH  MathSciNet  Google Scholar 

  9. Ni, J., Song, Q.: Adaptive Simultaneous Perturbation Based Pruning for a Class of Nonlinear Control Systems. submited to Neural computint and application

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2005 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Ni, J., Song, Q. (2005). Pruning Neural Networks for a Two-Link Robot Control System. In: Cabestany, J., Prieto, A., Sandoval, F. (eds) Computational Intelligence and Bioinspired Systems. IWANN 2005. Lecture Notes in Computer Science, vol 3512. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11494669_85

Download citation

  • DOI: https://doi.org/10.1007/11494669_85

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-26208-4

  • Online ISBN: 978-3-540-32106-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics