论文信息 - Continuous time modeling of nonlinear systems: a neural network-based approach

Continuous time modeling of nonlinear systems: a neural network-based approach

A neural network-based approach for continuous-time modeling of nonlinear systems is presented. The approach is based on an implicit integrator and recurrent networks. The resulting continuous-time model (a set of ordinary differential equations) is capable of correctly capturing the long term attractors of the system.<<ETX>>

Ioannis G. Kevrekidis | Ramiro Rico-Martínez | I. Kevrekidis | R. Rico-Martínez

[1] Shigeki Nakauchi,et al. Reconstruction of Munsell color space by a five-layered neural network , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[2] Barak A. Pearlmutter. Learning State Space Trajectories in Recurrent Neural Networks , 1989, Neural Computation.

[3] Rahmat Shoureshi,et al. A Neural Network Approach for Identification of Continuous-Time Nonlinear Dynamic Systems , 1991, 1991 American Control Conference.

[4] Pineda,et al. Generalization of back-propagation to recurrent neural networks. , 1987, Physical review letters.

[5] Halbert White,et al. On learning the derivatives of an unknown mapping with multilayer feedforward networks , 1992, Neural Networks.

[6] A. Lapedes,et al. Nonlinear Signal Processing Using Neural Networks , 1987 .

[7] Ioannis G. Kevrekidis,et al. DISCRETE- vs. CONTINUOUS-TIME NONLINEAR SIGNAL PROCESSING OF Cu ELECTRODISSOLUTION DATA , 1992 .

[8] M. Kramer. Nonlinear principal component analysis using autoassociative neural networks , 1991 .

[9] James P. Crutchfield,et al. Geometry from a Time Series , 1980 .