The unpredictability of standard back propagation neural networks in classification applications
The unpredictability of standard back propagation neural networks in classification applications
复制标题
标准反向传播神经网络在分类应用中的不可预测性
DOI：
10.1287/mnsc.41.3.555
复制
发表时间：
1995
影响因子：
5.4
通讯作者：
Shouhong Wang
中科院分区：
文献类型：
--
作者：
Shouhong Wang
本注是Tam和Kiang（Tam，K.是的，M. Y.江1992.神经网络的管理应用：银行破产预测案例。管理科学38（7）926- 947.）。首先讨论了标准反向传播神经网络学习算法的不足，然后对人工神经网络在管理科学领域的应用提出了警告。还建议是一种可能的方式来提高神经网络在管理应用中的性能。
This note offers an extension of Tam and Kiang (Tam, K. Y., M. Y. Kiang. 1992. Management applications of neural networks: The case of bank failure predictions. Management Sci. 38(7) 926--947.). First the weakness of the standard back propagation neural network learning algorithm is discussed, and then a warning is issued regarding applications of artificial neural networks in the management science field. Also suggested is a possible way of improving the performance of neural networks in managerial applications.