Yadaiah, N. ; Sivakumar, L. ; Deekshatulu, B. L. (2000) Parameter identification via neural networks with fast convergence Mathematics and Computers in Simulation, 51 (3-4). pp. 157-167. ISSN 0378-4754
Full text not available from this repository.
Official URL: http://linkinghub.elsevier.com/retrieve/pii/S03784...
Related URL: http://dx.doi.org/10.1016/S0378-4754(99)00114-7
Abstract
The parameter identification using artificial neural networks is becoming very popular. In this chapter, the parameters of dynamical system are identified using artificial neural networks. A fast gradient decent technique for the parameter identification of a linear dynamical system has been presented. The following concepts are used for training of neural networks while identifying the system parameters: (1) batch wise training of neural networks;(2) variable learning parameter and; (3) an intelligent check over the rate at which parameters are converging. The complete algorithm is summarized as a flow chart. A detailed mathematical formulation is given. The simulation results and a comparative study with existing method is included.
| Item Type: | Article |
|---|---|
| Source: | Copyright of this article belongs to Elsevier Science. |
| Keywords: | Artificial Neural Networks; Parameter Identification; Optimization; Supervised Learning; Performance Index |
| ID Code: | 9703 |
| Deposited On: | 02 Nov 2010 10:57 |
| Last Modified: | 31 May 2011 08:48 |
Repository Staff Only: item control page
