Effect of Learning Rate on the Recognition of Images

Active and Passive Electronic Components

A. El Desouky¹  M. Hamed¹ 

[1] Faculty of Engineering, Suez Canal University, Port Said, Egypt, scuegypt.edu.eg

关键词: hidden;    test;    training;    data reduction;    pattern recognition;    vision system;    Walsh;    discrimination;    classification;    texture;    computer;    neural;   

Others  :  1368515
DOI  :  10.1155/1996/45086

 received in 1995-01-05, accepted in 1995-04-03,  发布年份 1995

【 摘 要 】

This paper presents a study for the effect of learning rate on an approach for texture classification and detection based on the neural network principle. This neural network consists of three layers, which are input, output, and hidden layers. The back propagation technique is considered. A computer algorithm is deduced and applied. In this work, the synthetic textures are generated. The results are taken for the modern computer of AT 486 type. The mathematical analysis is summarized in order to illustrate the effect of learning rate parameter on the exact discrimination during processing. This effect is studied through applications. The minimum consumed time for the computational time of classification in industry is correlated to correspond only the use of only 2 units in the hidden layer of a neural network for real images instead of 11 units.

【 授权许可】

CC BY   
Copyright © 1996 Hindawi Publishing Corporation. 1996