Title :
Multiple and time-varying dynamic modelling capabilities of recurrent neural networks
Author_Institution :
RIKEN, Inst. of Phys. & Chem. Res., Saitama, Japan
Abstract :
We propose some theories regarding the dynamical system representational capabilities of recurrent neural networks with real-valued inputs and outputs. It is shown that multiple nonlinear dynamic systems can be approximated within a single nonlinear model structure. A relationship is identified between this class of recurrent network, hybrid models and agent based systems
Keywords :
feedforward neural nets; function approximation; modelling; nonlinear dynamical systems; recurrent neural nets; time-varying systems; agent based systems; dynamical system representational capabilities; hybrid models; multiple nonlinear dynamic systems; recurrent neural networks; single nonlinear model structure; Biological neural networks; Brain modeling; Chemical processes; Computer networks; Control systems; Information processing; Marine vehicles; Nonlinear dynamical systems; Recurrent neural networks; Switches;
Conference_Titel :
Neural Networks for Signal Processing [1997] VII. Proceedings of the 1997 IEEE Workshop
Conference_Location :
Amelia Island, FL
Print_ISBN :
0-7803-4256-9
DOI :
10.1109/NNSP.1997.622390
