arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1801.07599cs.LGmath.CT
收藏

求解多类分类问题的前向神经网络的二值输出层

Binary output layer of feedforward neural networks for solving multi-class classification problems

Dalian University of Technology(大连理工大学)

Sibo Yang, Chao Zhang, Wei Wu

摘要:

本文研究了解决r类(大于或等于3)样本多类分类问题的前馈神经网络输出层节点的设计。输出层的常见和常规设置,在本文中称为“一对一方法”,如下:输出层包含r个输出节点,对应于r个类。对于第i类的输入样本,第i个输出节点的理想输出为1,所有其他输出节点的理想输出为0。本文提出了一种新的“二进制方法”:假设r为(2^(q减1),2 ^q],q大于或等于2,则我们让输出层包含q个输出节点,并让r个类的理想输出以二进制方式设计。在本文中进行的数值实验表明,我们的二进制方法做同样好的工作,但使用更少的输出节点比,传统的一对一的方法。

英文摘要:

Considered in this short note is the design of output layer nodes of feedforward neural networks for solving multi-class classification problems with r (bigger than or equal to 3) classes of samples. The common and conventional setting of output layer, called "one-to-one approach" in this paper, is as follows: The output layer contains r output nodes corresponding to the r classes. And for an input sample of the i-th class, the ideal output is 1 for the i-th output node, and 0 for all the other output nodes. We propose in this paper a new "binary approach": Suppose r is (2^(q minus 1), 2^q] with q bigger than or equal to 2, then we let the output layer contain q output nodes, and let the ideal outputs for the r classes be designed in a binary manner. Numerical experiments carried out in this paper show that our binary approach does equally good job as, but uses less output nodes than, the traditional one-to-one approach.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑