Share Email Print
cover

Proceedings Paper

Selection of optimal parameter of speed of training of neural network perceptron type
Author(s): Yury N. Kulchin; Elena V. Denisova; Igor V. Denisov; Maxim B. Efimov
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

The problem of optimization of training of the neural networks perceptron type is considered. The method of the select of parameter of the speed of training based on combination of optimum parameters is offered: optimum parameter selected before the beginning training and the optimum parameter after the first cycle of training. The mathematical calculations and deductions of optimum parameter of the speed of training represented. The numerical modeling on an example of the neural networks perceptron type is realized. Is shown that the combination optimum parameter of the speed of training on a first step of training with optimum parameter of the speed of training received previously improves the result of training more than on 0,24% and the speed of training more than one and a half.

Paper Details

Date Published: 17 June 2003
PDF: 6 pages
Proc. SPIE 5129, Fundamental Problems of Optoelectronics and Microelectronics, (17 June 2003); doi: 10.1117/12.502124
Show Author Affiliations
Yury N. Kulchin, Far Eastern State Technical Univ. (Russia)
Elena V. Denisova, Far Eastern State Univ. (Russia)
Igor V. Denisov, Maritime State Univ. (Russia)
Maxim B. Efimov, Far Eastern State Univ. (Russia)


Published in SPIE Proceedings Vol. 5129:
Fundamental Problems of Optoelectronics and Microelectronics
Yuri N. Kulchin; Oleg B. Vitrik, Editor(s)

© SPIE. Terms of Use
Back to Top