Authors:
- Introduces a new model of a modular neural network
- based on a granular approach
- Serves as reference
- book for scientists and engineers interested in applying soft computing
- Presents recent research
- Includes supplementary material: sn.pub/extras
Part of the book series: SpringerBriefs in Applied Sciences and Technology (BRIEFSAPPLSCIENCES)
Part of the book sub series: SpringerBriefs in Computational Intelligence (BRIEFSINTELL)
Buy it now
Buying options
Tax calculation will be finalised at checkout
Other ways to access
This is a preview of subscription content, log in via an institution to check for access.
Table of contents (6 chapters)
-
Front Matter
-
Back Matter
About this book
In this book, a new method for hybrid intelligent systems is proposed. The proposed method is based on a granular computing approach applied in two levels. The techniques used and combined in the proposed method are modular neural networks (MNNs) with a Granular Computing (GrC) approach, thus resulting in a new concept of MNNs; modular granular neural networks (MGNNs). In addition fuzzy logic (FL) and hierarchical genetic algorithms (HGAs) are techniques used in this research work to improve results. These techniques are chosen because in other works have demonstrated to be a good option, and in the case of MNNs and HGAs, these techniques allow to improve the results obtained than with their conventional versions; respectively artificial neural networks and genetic algorithms.
Authors and Affiliations
-
Division of Graduate Studies, Tijuana Institute of Tech,Div of Gradu, Tijuana, Mexico
Daniela Sanchez
-
Div of Gdu Stud,CalzTecn sn,Fra.TomAqu, Tijuana Institute of Technology, Tijuana, Mexico
Patricia Melin
Bibliographic Information
Book Title: Hierarchical Modular Granular Neural Networks with Fuzzy Aggregation
Authors: Daniela Sanchez, Patricia Melin
Series Title: SpringerBriefs in Applied Sciences and Technology
DOI: https://doi.org/10.1007/978-3-319-28862-8
Publisher: Springer Cham
eBook Packages: Engineering, Engineering (R0)
Copyright Information: The Author(s) 2016
Softcover ISBN: 978-3-319-28861-1Published: 02 March 2016
eBook ISBN: 978-3-319-28862-8Published: 23 February 2016
Series ISSN: 2191-530X
Series E-ISSN: 2191-5318
Edition Number: 1
Number of Pages: VIII, 101
Number of Illustrations: 7 b/w illustrations, 50 illustrations in colour
Topics: Computational Intelligence, Artificial Intelligence, Mathematical Models of Cognitive Processes and Neural Networks