论文信息 - Modeling of continuous time dynamical systems with input by recurrent neural networks

Modeling of continuous time dynamical systems with input by recurrent neural networks

This paper proves that any finite time trajectory of a given n-dimensional dynamical continuous system with input can be approximated by the internal state of the output units of a continuous time recurrent neural network (RNN). The proof is based on the idea of embedding the n-dimensional dynamical system into a higher dimensional one. As a result, we are able to confirm that any continuous dynamical system can be modeled by an RNN.

Tommy W. S. Chow | Xiao-Dong Li | T. Chow | Xiao-dong Li

[1] Kurt Hornik,et al. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks , 1990, Neural Networks.

[2] Fernando J. Pineda,et al. Dynamics and architecture for neural computation , 1988, J. Complex..

[3] M. Gupta,et al. Approximation of discrete-time state-space trajectories using dynamic recurrent neural networks , 1995, IEEE Trans. Autom. Control..

[4] Ken-ichi Funahashi,et al. On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[5] M. Hirsch,et al. Differential Equations, Dynamical Systems, and Linear Algebra , 1974 .

[6] D.R. Hush,et al. Progress in supervised neural networks , 1993, IEEE Signal Processing Magazine.

[7] Yuichi Nakamura,et al. Approximation of dynamical systems by continuous time recurrent neural networks , 1993, Neural Networks.

[8] L. K. Li. Approximation theory and recurrent networks , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[9] J J Hopfield,et al. Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.