Kattan M W, Beck J R
Arch Pathol Lab Med. 1995 Aug;119(8):672-7.
Neural networks are growing in popularity. However, empirically comparing them with traditional methods of solving medical classification decisions is not trivial. Following a brief description and comparison with the statistical technique, discriminant analysis, the methodology for comparing neural networks with discriminant analysis is described. The advantages and disadvantages of neural networks are summarized to support a conclusion that neural networks are beneficial and destined to proliferate. Areas of fruitful future research are identified.
神经网络正越来越受欢迎。然而，从经验上把它们与解决医学分类决策的传统方法进行比较并非易事。在简要描述神经网络并将其与统计技术判别分析进行比较之后，本文描述了将神经网络与判别分析进行比较的方法。总结了神经网络的优缺点，以支持神经网络有益且注定会广泛应用这一结论。还确定了未来富有成果的研究领域。
