WIT Press

The Effect Of Learning Rate To An Unsupervised Neural Network For Inspection Process

Price

Free (open access)

Paper DOI

10.2495/AI960211

Volume

16

Pages

20

Published

1996

Size

503 kb

Author(s)

C.K. Lee & C.H. Chung

Abstract

In this paper, we shall investigate the effect of learning rate to an unsupervised neural network when applied to an inspection process. The network we use is the Learning by Experience (LBE)[1]. Here, we analyse the learning rate for classifying parts which are produced from a machine with a varying parameter. Experiment results using IC leadframes are included. 1. Introduction In the manufacturing process of any kinds of products, there are some specifications which the produced parts have to follow. Hence, we shall base on some kinds of distributions to classify which product is good or defective. Usually, two parameters are used to describe these distributions: the mean and the standard deviation. In order to distinguish defective parts from the good ones, one m

Keywords