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.
Highlights
In the last few years, multi-classifier learning has received significant attention in many fields
We have proposed a new cross entropy loss function, named MPCE, that utilizes the maximum probability of predictive value to reduce the cross entropy loss of each iteration
The gradient derivation process shows that MPCE has less loss than Mean Square Error (MSE) and Cross Entropy (CE) on theory
Summary
In the last few years, multi-classifier learning has received significant attention in many fields. Many methods have been proposed to solve multi-classifier problems. Despite SVM, DT, Bayesian and K-means were wildly researched in the past years, The associate editor coordinating the review of this manuscript and approving it for publication was Bo Jin. despite SVM, DT, Bayesian and K-means were wildly researched in the past years, The associate editor coordinating the review of this manuscript and approving it for publication was Bo Jin Their ability to deal with nonlinear multi-classifier problems is always poor. Neural networks are famous for their strong ability to deal with nonlinear multi-classifier problems. Neural networks can represent high-dimensional parameters better than other methods due to their complex hidden layers. In order to address the multi-classifier problems that are nonlinear or with high-dimensional parameters, neural networks have successfully been used in many hot fields of artificial intelligence, such as image classification [12], embedded computation [13], biomedical engineering [14], etc
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
