Next Article in Journal
Balanced Parallel Exploration of Orthogonal Regions
Previous Article in Journal
A Theoretical Framework to Determine RHP Zero Dynamics in Sequential Interacting Sub-Systems
Open AccessArticle

Improved Neural Networks Based on Mutual Information via Information Geometry

College of Computer Science, Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
State Grid Information & Telecommunication Co.,Ltd., 1401 Main Building No 2 BaiGuang Avenue, Xi Cheng District, Beijing 100031, China
Author to whom correspondence should be addressed.
Algorithms 2019, 12(5), 103;
Received: 18 February 2019 / Revised: 1 May 2019 / Accepted: 2 May 2019 / Published: 13 May 2019
PDF [1252 KB, uploaded 13 May 2019]


This paper presents a new algorithm based on the theory of mutual information and information geometry. This algorithm places emphasis on adaptive mutual information estimation and maximum likelihood estimation. With the theory of information geometry, we adjust the mutual information along the geodesic line. Finally, we evaluate our proposal using empirical datasets that are dedicated for classification and regression. The results show that our algorithm contributes to a significant improvement over existing methods. View Full-Text
Keywords: neural networks; information geometry; geodesic line neural networks; information geometry; geodesic line

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Share & Cite This Article

MDPI and ACS Style

Wang, M.; Xiao, C.-B.; Ning, Z.-H.; Yu, J.; Zhang, Y.-H.; Pang, J. Improved Neural Networks Based on Mutual Information via Information Geometry. Algorithms 2019, 12, 103.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics



[Return to top]
Algorithms EISSN 1999-4893 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top