Kemp R A, MacAulay C, Palcic B
BC Cancer Research Centre, Vancouver BC, Canada.
Anal Cell Pathol. 1997;14(1):19-30. doi: 10.1155/1997/646081.
Over the last ten years feed-forward neural networks have become a popular tool for statistical decision making. During this time, they have been applied in many fields, including cytological classification. Neural networks are often treated as a black box, whose inner workings are concealed from the researcher. This is unfortunate, since the inner workings of a neural network can be understood in a manner similar to that of a linear discriminant function, which is the standard tool that researchers use for decision making. This paper discusses feed-forward neural networks and some methods to improve their performance for classification problems. Their relationship to discriminant functions will be examined for a simple two-dimensional classification problem.
在过去十年中，前馈神经网络已成为统计决策的常用工具。在此期间，它们已被应用于许多领域，包括细胞学分类。神经网络通常被视为一个黑匣子，其内部工作原理对研究人员来说是隐藏的。这很不幸，因为神经网络的内部工作原理可以用类似于线性判别函数的方式来理解，而线性判别函数是研究人员用于决策的标准工具。本文讨论了前馈神经网络以及一些提高其分类问题性能的方法。对于一个简单的二维分类问题，将研究它们与判别函数的关系。
