Paper Info
Title
MPCE: A Maximum Probability Based Cross Entropy Loss Function for Neural Network Classification
Abstract
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.
Year
DOI
Venue
2019
10.1109/ACCESS.2019.2946264
IEEE ACCESS
Keywords
DocType
Volume
Cross entropy,loss function,maximum probability,neural network classification,softmax
Journal
7
ISSN
Citations 
PageRank 
2169-3536
0
0.34
References 
Authors
0
6
Name
Order
Citations
PageRank
Yangfan Zhou123229.72
Xin Wang2587177.85
Mingchuan Zhang32910.19
Junlong Zhu43714.28
Ruijuan Zheng55114.47
Qingtao Wu67019.88