Hierarchical Modular Granular Neural Networks with Fuzzy Aggregation

In this book, anew method for hybrid intelligent systems is proposed. The proposed method isbased on a granular computing approach applied in two levels. The techniquesused and combined in the proposed method are modular neural networks (MNNs)with a Granular Computing (GrC) approach, thus resulting in a new concept ofMNNs; modular granular neural networks (MGNNs). In addition fuzzy logic (FL)and hierarchical genetic algorithms (HGAs) are techniques used in this researchwork to improve results. These techniques are chosen because in other workshave demonstrated to be a good option, and in the case of MNNs and HGAs, thesetechniques allow to improve the results obtained than with their conventionalversions; respectively artificial neural networks and genetic algorithms.

Sommario

Introduction.- Backgroundand Theory.- Proposed Method.- Applicationto Human Recognition.- ExperimentalResults.- Conclusions.

Riassunto

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.

Dettagli sul prodotto

• Autori: Patricia Melin, Daniel Sanchez, Daniela Sanchez
• Editore: Springer, Berlin
• Lingue: Inglese
• Formato: Tascabile
• Pubblicazione: 01.01.2016
• EAN: 9783319288611
• ISBN: 978-3-31-928861-1
• Pagine: 101
• Dimensioni: 156 mm x 235 mm x 4 mm
• Peso: 184 g
• Illustrazioni: VIII, 101 p. 57 illus., 50 illus. in color.
• Serie: SpringerBriefs in Applied Sciences and Technology; SpringerBriefs in Computational Intelligence; SpringerBriefs in Applied Sciences and Technology; SpringerBriefs in Computational Intelligence
• Categorie: Scienze naturali, medicina, informatica, tecnica > Tecnica > Tematiche generali, enciclopedie; C, Artificial Intelligence, Mathematische Modellierung, engineering, Computational Intelligence, Mathematical modelling, Neural networks (Computer science)