The Unpredictability of Standard Back Propagation Neural Networks in Classification Applications
指出标准反向传播神经网络学习算法的弱点，警告其在管理科学领域的应用风险，并提出了改进性能的可能方法。
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.