Yamashita, Hideo and Kowata, Norio and Cingoski, Vlatko and Kaneda, Kazufumi (1995) Direct Solution Method for Finite Element Analysis Using Hopfield Neural Network. 6th Biennial IEEE Conference on Electromagnetic Field Computation, 31 (3). pp. 1964-1966.
Preview |
Text
direct.pdf Download (1MB) | Preview |
Abstract
One property of the Hopfield neural network is the monotonous minimization of energy as time proceeds. In this paper, this property is applied to minimize the energy functional obtained by ordinary finite element analysis. The mathematical representation and correlation between finite element and neural network calculus are presented. The selection of the sigmoid function and its influence on the iteration process is discussed. The obtained results using the proposed method show excellent agreement with theoretical solutions.
| Item Type: | Article |
|---|---|
| Subjects: | Engineering and Technology > Electrical engineering, electronic engineering, information engineering |
| Divisions: | Faculty of Electrical Engineering |
| Depositing User: | Vlatko Cingoski |
| Date Deposited: | 19 Dec 2012 08:38 |
| Last Modified: | 24 Jun 2013 06:49 |
| URI: | https://eprints.ugd.edu.mk/id/eprint/4034 |
Actions (login required)
 |
View Item |