The relative order and inverses of recurrent networks

@article{Kambhampati1996TheRO,
  title={The relative order and inverses of recurrent networks},
  author={Chandrasekhar Kambhampati and S. Manchanda and A. Delgado and Gary G. R. Green and Kevin Warwick and M. T. Tham},
  journal={Automatica},
  year={1996},
  volume={32},
  pages={117-123}
}
Differential geometry is used to investigate the structure of neural-network-based control systems. The key aspect is relative order-an invariant property of dynamic systems. Finite relative order allows the specification of a minimal architecture for a recurrent network. Any system with finite relative order has a left inverse. It is shown that a recurrent network with finite relative order has a local inverse that is also a recurrent network with the same weights. The results have… CONTINUE READING

From This Paper

Topics from this paper.

References

Publications referenced by this paper.
Showing 1-10 of 16 references

Invertibility of nonlinear control systems

  • R. M. Hirschorn
  • SIAM J. Control Optim. 17,289-297.
  • 1979
Highly Influential
5 Excerpts

Recurrent neural networks: some control problems

  • R. Zbikowski
  • PhD thesis, Department of Mechanical Engineering…
  • 1994
1 Excerpt

The relative order of a class of recurrent networks

  • S. Manchanda, C. Kambhampati, M. T. Tham, G.G.R. Green
  • Proc. IEE ‘Control 94’, Vol. 2, pp. 973-977.
  • 1994
3 Excerpts

Neural networks for control systems-a survey

  • K. J. Hunt, D. Sbarbaro, R. Zbikowski, P. J. Gawthrop
  • kutomatica, 28, 1083-1112.
  • 1992
2 Excerpts

Geometric methods for nonlinear process control 1

  • C. Kravaris, .I.C. Kantor
  • background. Ind. Engng Chem. Rex, 29,2295-2310.
  • 1990
2 Excerpts

Geometric methods for nonlinear process control 1 . background

  • S. Manchanda
  • Ind . Engng Chem . Rex
  • 1990

Similar Papers

Loading similar papers…