期刊
IEEE ACCESS
卷 7, 期 -, 页码 146331-146341出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2019.2946264
关键词
Cross entropy; loss function; maximum probability; neural network classification; softmax
资金
- National Natural Science Foundation of China (NSFC) [U1604155, 61602155, 61871430]
- Scientific and Technological Innovation Team of Colleges and Universities in Henan Province [20IRTSTHN018]
- China Postdoctoral Science Foundation [2018M630461]
- Science Foundation of Ministry of Education of China [19YJC630174]
- University of Henan Province [19zx010]
- Science and Technology Development Programs of Henan Province [192102210284]
In recent years, multi-classifier learning is of significant interest in industrial and economic fields. Moreover, neural network is a popular approach in multi-classifier learning. However, the accuracies of neural networks are often limited by their loss functions. For this reason, we design a novel cross entropy loss function, named MPCE, which based on the maximum probability in predictive results. In this paper, we first analyze the difference of gradients between MPCE and the cross entropy loss function. Then, we propose the gradient update algorithm based on MPCE. In the experimental part of this paper, we utilize four groups of experiments to verify the performance of the proposed algorithm on six public datasets. The first group of experimental results show that the proposed algorithm converge faster than the algorithms based on other loss functions. Moreover, the results of the second group show that the proposed algorithm obtains the highest training and test accuracy on the six datasets, and the proposed algorithm perform better than others when class number changing on the sensor dataset. Furthermore, we use the model of convolutional neural network to implement the compared methods on the mnist dataset in the fourth group of experiments. The results show that the proposed algorithm has the highest accuracy among all executed methods.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据