Deep learning architecture using rough sets and rough neural networks
Abstract
Purpose
This paper aims to utilize machine learning and soft computing to propose a new method of rough sets using deep learning architecture for many real-world applications.
Design/methodology/approach
The objective of this work is to propose a model for deep rough set theory that uses more than decision table and approximating these tables to a classification system, i.e. the paper propose a novel framework of deep learning based on multi-decision tables.
Findings
The paper tries to coordinate the local properties of individual decision table to provide an appropriate global decision from the system.
Research limitations/implications
The rough set learning assumes the existence of a single decision table, whereas real-world decision problem implies several decisions with several different decision tables. The new proposed model can handle multi-decision tables.
Practical implications
The proposed classification model is implemented on social networks with preferred features which are freely distribute as social entities with accuracy around 91 per cent.
Social implications
The deep learning using rough sets theory simulate the way of brain thinking and can solve the problem of existence of different information about same problem in different decision systems
Originality/value
This paper utilizes machine learning and soft computing to propose a new method of rough sets using deep learning architecture for many real-world applications.
Keywords
Citation
Hassan, Y.F. (2017), "Deep learning architecture using rough sets and rough neural networks", Kybernetes, Vol. 46 No. 4, pp. 693-705. https://doi.org/10.1108/K-09-2016-0228
Publisher
:Emerald Publishing Limited
Copyright © 2017, Emerald Publishing Limited