Trajectory Control of Convergent Networks

Authors:
N. Peterfreund;Y. Baram
Affiliations:
Oak Ridge National Lab, P.O. Box 2008, Oak Ridge TN 37831-6355. E-mail: Email: v4p@ornl.gov/;Department of Computer Science, Technion, Israel Institute of Technology, Haifa 32000, Israel. Tel(USA): 415-604-0202, Fax(USA): 415-604-0174. E-mail: Email: ybaram@grade.arc.nasa.gov
Venue:
Neural Processing Letters
Year:
1998

Citing 4
Cited 0

Terminal attractors in neural networks

Neural Networks
Original Contribution: The construction of arbitrary stable dynamics in nonlinear neural networks

Neural Networks
Learning a trajectory using adjoint functions and teacher forcing

Neural Networks
Gradient calculations for dynamic recurrent neural networks: a survey

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a class of feedback control functions which increase theconvergence rates of nonlinear dynamical systems. A simple sign functionis used to obtain convergence in finite time. We describe a trajectorylearning procedure which preserves the convergence property of the system.Based on the proposed feedback, we developed a new neural network modelwhich converges in finite time.