Approximation of dynamical systems by continuous time recurrent neural networks

Neural Networks

Volumn 6, Issue 6, 1993, Pages 801-806

  Funahashi, Ken ichi ^a   Nakamura, Yuichi ^a  

^a TOYOHASHI UNIVERSITY OF TECHNOLOGY   (Japan)

Author keywords

Approximation; Autonomous system; Continuous curve; Continuous time recurrent neural network; Dynamical system; Hidden unit; Internal state; Trajectory

Indexed keywords

ESTIMATION; SYSTEMS ANALYSIS; THEOREM PROVING;

AUTONOMOUS SYSTEMS; CONTINUOUS CURVES; CONTINUOUS TIME RECURRENT NEURAL NETWORKS; DYNAMICAL SYSTEMS; HIDDEN UNITS; INTERNAL STATES; TRAJECTORY;

NEURAL NETWORKS;

EID: 0027154319     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(05)80125-X     Document Type: Article

References (14)

1. Approximation by superpositions of a sigmoidal function
2. On the approximate realization of continuous mappings by neural networks
3. Convergent activation dynamics in continuous time networks
4. Multilayer feed-forward networks are universal approximators
5. Learning state space trajectories in recurrent neural networks
6. Learning state space trajectories in recurrent neural networks
7. Generalization of backpropagation to recurrent neural networks
8. Learning internal representations by error propagation
9. A learning algorithm to teach spatio-temporal patterns to recurrent neural networks
10. Learning nonlinear dynamics by recurrent neural networks
11. A structure by which a recurrent neural network can approximate a nonlinear dynamic system
12. A learning algorithm for continually running fully recurrent neural networks