A Method for Synthesizing Neural-Network Models under Incomplete Data
V. G. Schetinin, V. S. Abrukov, and A. I. Brazhnikov
Chuvash State University, Cheboksary, Russia E-mail: abrukov@yandex.ru
Pages: 433-440
Abstract
Problems of synthesizing neural-network models under incomplete experimental data are described. The accuracy of the models is heavily dependent on their complexity. The proposed method allows self-organizing neural-network models of near-optimal complexity. Examples of synthesizing models of flame interferometry and growth of industrial production are presented.
|
