Design of Artificial Neural Networks With a Specified Quality of Functioning

被引：7

作者：

Danilin, S. N. ^{[1
]}

Makarov, M. V. ^{[1
]}

Shchanikov, S. A. ^{[1
]}

机构：

[1] Vladimir State Univ, Murom Inst, Dept CAD Syst, Phys & Appl Math & Informat Technol, Murom, Russia

来源：

2014 INTERNATIONAL CONFERENCE ON ENGINEERING AND TELECOMMUNICATION (EN&T 2014) | 2014年

关键词：

artificial neural networks; parameters of functioning quality; accuracy; functional tolerance; fault tolerance; digit capacity;

D O I：

10.1109/EnT.2014.38

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

The general approach to development of methods for determination of quality of functioning of artificial neural networks any structure and destination has been formulated. This paper demonstrates complex index of quality (accuracy) of functioning of the artificial neural networks. The index considers values of functional tolerances. The article describes properties of the complex index and its use in examples of designing of artificial neural networks. These networks were used for approximating of basic mathematical functions and estimating of amplitude of harmonic signals containing noise component. Dependence of quality of functioning of artificial neural networks on a chosen training function was shown.

引用

页码：67 / 71

页数：5

共 7 条

[1] Danilin S. N., 2014, METODI USTROISTVA PE, P70
[2] Galushkin A.I., 2010, NEURAL NETWORKS THEO, P496
[3] Haykin S., 2005, NEURAL NETWORKS COMP
[4] Perov A. I., 2003, STAT THEORY RADIO SY
[5] Implementation issues of neuro-fuzzy hardware: Going toward HW/SW codesign
Reyneri, LM
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2003, 14 (01): : 176 - 194
[6] Shchanikov S.A., 2013, INFORM TEHNOLOGII, P57
[7] Swingler K., 2001, Applying Neural Networks: A Practical Guide

← 1 →