Kenji Doya,
Universality of Fully-Connected Recurrent Neural Networks.
Department of Biology, University of California, San
Diego, La Jolla, CA 92093-0322, USA, February 1993.
Kenji Doya,
Universality of Fully-Connected Recurrent Neural Networks.
Department of Biology, University of California, San
Diego, La Jolla, CA 92093-0322, USA, February 1993.
It is shown from the universality of multi-layer neural networks that any discrete-time or continuous-time dynamical system can be approximated by discrete-time or continuous-time recurrent neural networks, respectively.