An overview on rough neural networks. Issue 7 (October 2016)

• Record Type: Journal Article
• Authors: Liao, Hongmei; Ding, Shifei; Wang, Miaomiao; Ma, Gang
• Is Part Of: Neural computing & applications. Volume 27:Issue 7(2016)
• Page Start: 1805
• Page End: 1816
• Publication Date: 2016-10
• Subjects: Granular computing -- Rough set -- Neural networks -- Rough neural networks; Neural networks (Computer science) -- Periodicals; Neural circuitry -- Periodicals; Artificial intelligence -- Periodicals; Neural Networks (Computer) -- Periodicals; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux nerveux -- Périodiques; Intelligence artificielle -- Périodiques; 006.32
• DOI: 10.1007/s00521-015-2009-6
• Languages: English
• ISSNs: 0941-0643

Abstract

Abstract This paper is based on rough set theory and neural networks, and mainly introduces the previous researchers how to use rough set theory, which has the superior ability to rule out redundant, and neural networks, which has the self-organizing and self-learning ability to complement each other's advantages, in order to obtain rough neural networks with better performance. This paper also details the possibility of the integration of these two theories and the current mainstream fusion method and then takes two more mainstream previous neural networks, back-propagation neural networks and radial basis function neural networks, as an example to integrate with rough set theory. This example describes the fusion method, fusion performance, and its corresponding learning algorithm after fusion in detail.