Dynamic Neural Nets in the State Space Utilized in Non-Linear Process Identification
This work shows the use of a novel neural model for identification of non-linear process. The neural model make use of internal dynamic with dynamical neurons. The parameters responsible for the dynamic of the neural net are adjustable, giving a high flexibility for the neural model in process identification.
KeywordsIntermediate Layer Neural Model Hyperbolic Tangent Neuron Layer Specific Neural Network
Unable to display preview. Download preview PDF.
- F.M. de Azevedo. Contribution to the Study of Neural Networks in Dynamical Expert Systems. PhD thesis, Institut D’Informatique, FUNDP, Namur, Belgium, 1993.Google Scholar
- R.C.L. de Oliveira, C.L. Nascimento Jr., and T. Yoneyama. A fault tolerant controller based on neural nets. In Proceedings of the IEE International Conference on Control’91, volume 1, pages 399–404, Endiburgh, UK, 1991.Google Scholar
- M. Jordan. The Learning of Representations for Sequential Performance. PhD thesis, University of California, San Diego, California, USA, 1989.Google Scholar
- C.L. Nascimento Jr. Artificial Neural Networks in Control and Optimization. PhD thesis, Control System Centre, Faculty of Technology, University of Manchester, Manchester, UK, 1994.Google Scholar
- L. Personnaz, I. Guyon, and G. Dreyfus. Information storage and retrieval in spin-glass like neural networks. Journal de Physique, Lettres (Orsay, France), 46:L–359–L–365, 1985.Google Scholar
- J. Sjoberg. Non-Linear System Identification with Neural Networks. PhD thesis, Department of Electrical Engineering, Linkoping University, Linkoping, Sweden, 1995.Google Scholar
- R. Williams and D. Zipser. Experimental analysis of the real-time recurrent learning algorithm. Connect. Sci., 1:179–211, 1990.Google Scholar
- R.W. Żbikowski. Recurrent Neural Networks: Some Control Aspects. PhD thesis, Faculty of Engineering, Glasgow University, Glasgow, UK, 1994.Google Scholar