17 June 2003 Selection of optimal parameter of speed of training of neural network perceptron type
Author Affiliations +
Proceedings Volume 5129, Fundamental Problems of Optoelectronics and Microelectronics; (2003); doi: 10.1117/12.502124
Event: Fundamental Problems of Optoelectronics and Microelectronics, 2002, Vladivostok, Russian Federation
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.
© (2003) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yury N. Kulchin, Elena V. Denisova, Igor V. Denisov, Maxim B. Efimov, "Selection of optimal parameter of speed of training of neural network perceptron type", Proc. SPIE 5129, Fundamental Problems of Optoelectronics and Microelectronics, (17 June 2003); doi: 10.1117/12.502124; https://doi.org/10.1117/12.502124
PROCEEDINGS
6 PAGES


SHARE
KEYWORDS
Neural networks

Neurons

Numerical modeling

Mathematical modeling

Chemical elements

Data processing

Control systems

Back to Top