![](/images/graphics-bg.png)
Simplified Information Maximization for Improving Generalization Performance in Multilayered Neural Networks
Author
Source
Mathematical Problems in Engineering
Issue
Vol. 2016, Issue 2016 (31 Dec. 2016), pp.1-17, 17 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2016-03-28
Country of Publication
Egypt
No. of Pages
17
Main Subjects
Abstract EN
A new type of information-theoretic method is proposed to improve prediction performance in supervised learning.
The method has two main technical features.
First, the complicated procedures used to increase information content are replaced by the direct use of hidden neuron outputs.
Information is controlled by directly changing the outputs of the hidden neurons.
In addition, to simultaneously increase information content and decrease errors between targets and outputs, the information acquisition and use phases are separated.
In the information acquisition phase, the autoencoder tries to acquire as much information content on input patterns as possible.
In the information use phase, information obtained in the acquisition phase is used to train supervised learning.
The method is a simplified version of actual information maximization and directly deals with the outputs from neurons.
The method was applied to the three data sets, namely, Iris, bankruptcy, and rebel participation data sets.
Experimental results showed that the proposed simplified information acquisition method was effective in increasing the real information content.
In addition, by using the information content, generalization performance was greatly improved.
American Psychological Association (APA)
Kamimura, Ryotaro. 2016. Simplified Information Maximization for Improving Generalization Performance in Multilayered Neural Networks. Mathematical Problems in Engineering،Vol. 2016, no. 2016, pp.1-17.
https://search.emarefa.net/detail/BIM-1111968
Modern Language Association (MLA)
Kamimura, Ryotaro. Simplified Information Maximization for Improving Generalization Performance in Multilayered Neural Networks. Mathematical Problems in Engineering No. 2016 (2016), pp.1-17.
https://search.emarefa.net/detail/BIM-1111968
American Medical Association (AMA)
Kamimura, Ryotaro. Simplified Information Maximization for Improving Generalization Performance in Multilayered Neural Networks. Mathematical Problems in Engineering. 2016. Vol. 2016, no. 2016, pp.1-17.
https://search.emarefa.net/detail/BIM-1111968
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1111968