EXPERIMENTATION WITH A BACKPROPAGATION NEURAL NETWORK - AN APPLICATION TO PLANNING END USER SYSTEM-DEVELOPMENT

被引：12

作者：

LODEWYCK, RW ^{[1
]}

DENG, PS ^{[1
]}

机构：

[1] CALIF STATE UNIV STANISLAUS,TURLOCK,CA

来源：

INFORMATION & MANAGEMENT | 1993年 / 24卷 / 01期

关键词：

BACKPROPAGATION ALGORITHM; NEURAL NETWORKS; CONNECTIONIST MODELS; UNSTRUCTURED DECISION MAKING; END USER SYSTEM DEVELOPMENT; INFORMATION SYSTEM PLANNING;

D O I：

10.1016/0378-7206(93)90042-R

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Neural networks utilize the paradigm of the human brain to acquire knowledge through a training process. The knowledge base is stored in the form of weighted interconnections between layer nodes; this allows the network to generalize. Computational experimentation with a back-propagation algorithm yielded useful information concerning the effect of several key model parameters on network training and performance. These findings are illustrated through the application of a modest sized three layer neural network to the planning of end user involvement in the development of information systems.

引用

页码：1 / 8

页数：8

共 16 条

[1]

ALAVI M, 1985, J MANAGEMENT INF WIN

[2]

CARPENTER GA, 1988, COMPUTER MAR, P77

[3]

DAVIS GB, 1988, END USER COMPUTING C

[4] ANALYSIS OF HIDDEN UNITS IN A LAYERED NETWORK TRAINED TO CLASSIFY SONAR TARGETS [J].