Improved Neural Networks Based on Mutual Information via Information Geometry

Autor:	Zhenhu Ning, Ya-Hao Zhang, Meng Wang, Jin Pang, Chuangbai Xiao, Jing Yu
Jazyk:	angličtina
Rok vydání:	2019
Předmět:	information geometry Geodesic lcsh:T55.4-60.8 Computer science Maximum likelihood 02 engineering and technology computer.software_genre lcsh:QA75.5-76.95 Theoretical Computer Science 03 medical and health sciences 0302 clinical medicine 0202 electrical engineering electronic engineering information engineering lcsh:Industrial engineering. Management engineering Information geometry Numerical Analysis Artificial neural network Emphasis (telecommunications) Mutual information neural networks Regression geodesic line Computational Mathematics Computational Theory and Mathematics 020201 artificial intelligence & image processing Data mining lcsh:Electronic computers. Computer science computer 030217 neurology & neurosurgery
Zdroj:	Algorithms, Vol 12, Iss 5, p 103 (2019) Algorithms Volume 12 Issue 5
ISSN:	1999-4893
Popis:	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.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b7f1393456f1510e78c9e13d514bca7f https://www.mdpi.com/1999-4893/12/5/103 Zobrazit plný text záznamu Plný text ve formátu PDF Plný text ve formátu HTML
Nepřihlášeným uživatelům se plný text nezobrazuje	K zobrazení výsledku je třeba se přihlásit.