arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1601.01157cs.LG
收藏

用神经网络改进多类分类的一种简单方法

A simple technique for improving multi-class classification with neural networks

University Ruhr West(鲁尔西区应用技术大学);ENSTA ParisTech(巴黎高等先进技术学院)

Thomas Kopinski, Alexander Gepperth, Uwe Handmann

摘要:

我们提出了一种新的方法来执行多类模式分类与神经网络,并测试了一个具有挑战性的三维手势识别问题。我们的方法包括一个标准的一对一(OAA)分类,然后是另一个网络层分类产生的类分数,可能由原始原始输入向量增强。这使得网络能够消除难以分离的类别的歧义,因为类别分数的分布也携带了大量信息,并且实际上经常用于评估决策的置信度。我们表明,通过这种方法,我们能够显着提高我们的结果,整体以及特定的困难情况下,硬10类手势分类任务。

英文摘要:

We present a novel method to perform multi-class pattern classification with neural networks and test it on a challenging 3D hand gesture recognition problem. Our method consists of a standard one-against-all (OAA) classification, followed by another network layer classifying the resulting class scores, possibly augmented by the original raw input vector. This allows the network to disambiguate hard-to-separate classes as the distribution of class scores carries considerable information as well, and is in fact often used for assessing the confidence of a decision. We show that by this approach we are able to significantly boost our results, overall as well as for particular difficult cases, on the hard 10-class gesture classification task.

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。

↑