Hierarchical Modular Granular Neural Networks with Fuzzy Aggregation

• Κύριοι συγγραφείς: Sanchez, Daniela (Συγγραφέας), Melin, Patricia (Συγγραφέας)
• Συγγραφή απο Οργανισμό/Αρχή: SpringerLink (Online service)
• Μορφή: Ηλεκτρονική πηγή Ηλ. βιβλίο
• Γλώσσα: English
• Έκδοση: Cham : Springer International Publishing : Imprint: Springer, 2016.
• Έκδοση: 1st ed. 2016.
• Σειρά: SpringerBriefs in Applied Sciences and Technology,
• Θέματα: Engineering.; Artificial intelligence.; Neural networks (Computer science).; Computational intelligence.; Computational Intelligence.; Artificial Intelligence (incl. Robotics).; Mathematical Models of Cognitive Processes and Neural Networks.
• Φυσική περιγραφή: VIII, 101 p. 57 illus., 50 illus. in color. online resource.
• ISBN: 9783319288628
• ISSN: 2191-530X

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.