Abstract
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.
Highlights
An artificial neural network is a framework for many different machine learning algorithms to work together and process complex data inputs; it is vaguely inspired by biological neural networks that constitute animal brains [1]
Information geometry is a branch of mathematics that applies the theory of Riemannian the problems above, we introduce the theory of information geometry into neural networks
The proposed algorithm for training neural networks is based on information theory and
Summary
An artificial neural network is a framework for many different machine learning algorithms to work together and process complex data inputs; it is vaguely inspired by biological neural networks that constitute animal brains [1]. Several variants of neural networks have been derived from the context of applications. The convolutional neural network is one of the most popular variants. It is composed of one or more convolutional layers with fully connected layers and pooling layers [5]. The deep belief network (DBN) is considered to be a composition of simple learning modules that make up each layer [6]. The output layer can obtain information from past and future states simultaneously
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
