Learning dynamical systems by recurrent
โ
M. Kimura; R. Nakano
๐
Article
๐
1998
๐
Elsevier Science
๐
English
โ 253 KB
This paper investigates the problem of approximating a dynamical system (DS) by a recurrent neural network (RNN) as one extension of the problem of approximating orbits by an RNN. We systematically investigate how an RNN can produce a DS on the visible state space to approximate a given DS and as a