Trajectory Control of Convergent Networks
We present a class of feedback control functions which increase the convergence rates of nonlinear dynamical systems. A simple sign function is used to obtain convergence in finite time. We describe a trajectory learning procedure which preserves the convergence property of the system. Based on the proposed feedback, we developed a new neural network model which converges in finite time.
Unable to display preview. Download preview PDF.
- 1.H.D. Chiang and J.S. Thorp, “Stability regions of nonlinear dynamical systems: A constructive methodology”, IEEE Transactions on Automatic Control, Vol. 34, No. 12, pp. 1229–1241, 1989.Google Scholar
- 2.M.A. Cohen, “The construction of arbitrary stable dynamics in nonlinear neural networks”, Neural Networks, Vol. 5, pp. 83–103, 1992.Google Scholar
- 3.J.J. Hopfield, “Neurons with graded response have collective computational properties like those of two-state neurons”, Proc. Nath. Acad. Sci. USA, Vol. 81, pp. 3088–3092, 1984.Google Scholar
- 4.H.K. Khail, Nonlinear Systems, Prentice Hall, Upper Saddle River, NJ, 1996.Google Scholar
- 5.B.A. Pearlmutter, “Gradient calculations for dynamic recurrent neural networks: A survey”, IEEE Transactions on Neural Networks, Vol. 6, No. 5, pp. 1212–1228, 1995.Google Scholar
- 6.N.B. Toomarian and J. Barhen, “Learning a trajectory using adjoint functions and teacher forcing”, Neural Networks, Vol. 5, pp. 473–484, 1992.Google Scholar
- 7.M. Zak, “Terminal attractors in neural networks”, Neural Networks, Vol. 2, pp. 259–274, 1989.Google Scholar