Universality of Fully-Connected Recurrent Neural Networks

It is shown from the universality of multi-layer neural networks that any discretetime or continuous-time dynamical system can be approximated by discrete-time or continuous-time recurrent neural networks, respectively.

[1]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

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

[3]  Barak A. Pearlmutter.  Learning State Space Trajectories in Recurrent Neural Networks , 1989, Neural Computation.

[4]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[5]  Kenji Doya,et al.  Adaptive neural oscillator using continuous-time back-propagation learning , 1989, Neural Networks.

[6]  Kumpati S. Narendra,et al.  Neural Networks In Dynamical Systems , 1990, Other Conferences.

[7]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[8]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[9]  K. Doya,et al.  Bifurcations in the learning of recurrent neural networks , 1992, [Proceedings] 1992 IEEE International Symposium on Circuits and Systems.