|
Avtomatika i Telemekhanika, 2012, Issue 11, Pages 129–143
(Mi at4076)
|
|
|
|
This article is cited in 11 scientific papers (total in 11 papers)
Topical issue
Numerical methods of interval analysis in learning neural network
P. V. Saraev Lipetsk State Technical University, Lipetsk, Russia
Abstract:
The paper is devoted to the development and examination of the interval analysis-based numerical methods of the guaranteed learning of neural direct-propagation networks. Developed were contractive operators that allow for the singularities of the problem of learning (quadratic learning performance functional and superpositional weight-linear/nonlinear structure of the neural networks) and are used in the numerical methods of learning. The results of computer-aided experiments studying effectiveness of the developed methods were presented. The method of learning based on the algorithm of inverse error propagation and the method of weight shaking for determination of the global optimum were compared.
Citation:
P. V. Saraev, “Numerical methods of interval analysis in learning neural network”, Avtomat. i Telemekh., 2012, no. 11, 129–143; Autom. Remote Control, 73:11 (2012), 1865–1876
Linking options:
https://www.mathnet.ru/eng/at4076 https://www.mathnet.ru/eng/at/y2012/i11/p129
|
Statistics & downloads: |
Abstract page: | 618 | Full-text PDF : | 308 | References: | 59 | First page: | 34 |
|