TY - JOUR
T1 - Modeling of continuous time dynamical systems with input by recurrent neural networks
AU - Chow, Tommy W. S.
AU - Li, Xiao-Dong
PY - 2000
Y1 - 2000
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=0033747856&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0033747856&origin=recordpage
U2 - 10.1109/81.841860
DO - 10.1109/81.841860
M3 - RGC 22 - Publication in policy or professional journal
SN - 1057-7122
VL - 47
SP - 575
EP - 578
JO - IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications
JF - IEEE Transactions on Circuits and Systems I: Fundamental Theory and Applications
IS - 4
ER -