Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
758823 | Communications in Nonlinear Science and Numerical Simulation | 2011 | 13 Pages |
Abstract
Because to apply a deterministic RNN to a noisy time series and the existence of a linear approximation are doubtful, we reconsider the solubility and stability of a recurrent neural network (RNN). Simpler methods are proposed to replace the complicated nonsingular M-matrix method when nonlinearities exist and to replace the complicated linear matrix inequality method when time-varying delays exist.
Related Topics
Physical Sciences and Engineering
Engineering
Mechanical Engineering
Authors
Eva C. Yen,