A loss function for classification based on a robust similarity metric
A loss function for classification based on a robust similarity metric
复制标题
DOI：
10.1109/ijcnn.2010.5596485
复制
发表时间：
2010-07
期刊：
影响因子：
--
通讯作者：
Abhishek Singh;J. Príncipe
中科院分区：
文献类型：
--
作者：
Abhishek Singh;J. Príncipe
我们提出了一个基于边缘的损失函数分类，最近提出的相似性度量称为相关熵的启发。我们发现，相关熵诱导的非凸损失函数，是一个更接近的误分类损失（理想的0-1损失）。我们表明，通过优化建议的损失函数，使用神经网络得到的判别函数是不敏感的离群值，并具有更好的泛化性能相比，使用平方损失函数，这是常见的神经网络分类器。所提出的训练分类器的方法是一种在真实的世界分类问题上获得更好结果的实用方法，该方法使用简单的基于梯度的在线训练过程来最小化经验风险。
We present a margin-based loss function for classification, inspired by the recently proposed similarity measure called correntropy. We show that correntropy induces a nonconvex loss function that is a closer approximation to the misclassification loss (ideal 0–1 loss). We show that the discriminant function obtained by optimizing the proposed loss function using a neural network is insensitive to outliers and has better generalization performance as compared to using the squared loss function which is common in neural network classifiers. The proposed method of training classifiers is a practical way of obtaining better results on real world classification problems, that uses a simple gradient based online training procedure for minimizing the empirical risk.