A novel modular RBF neural network based on a brain-like partition method

In this study, a modular design methodology inherited from cognitive neuroscience and neurophysiology is proposed to develop artificial neural networks, aiming to realize the powerful capability of brain—divide and conquer—when tackling complex problems. First, a density-based brain-like partition m...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Neural computing & applications Jg. 32; H. 3; S. 899 - 911
Hauptverfasser: Qiao, Jun-Fei, Meng, Xi, Li, Wen-Jing, Wilamowski, Bogdan M.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Springer London 01.02.2020
Springer Nature B.V
Schlagworte:
Architecture
Artificial Intelligence
Artificial neural networks
Brain
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Data Mining and Knowledge Discovery
Image Processing and Computer Vision
Learning theory
Modular construction
Modular design
Modular structures
Neural networks
Neurophysiology
Original Article
Partitions
Probability and Statistics in Computer Science
Radial basis function
Radial basis function (RBF) network
Brain-like partition
Second-order algorithm
Modular neural network
ISSN:0941-0643, 1433-3058
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this study, a modular design methodology inherited from cognitive neuroscience and neurophysiology is proposed to develop artificial neural networks, aiming to realize the powerful capability of brain—divide and conquer—when tackling complex problems. First, a density-based brain-like partition method is developed to construct the modular architecture, with a highly connected center in each sub-network as the human brain. The whole task is also divided into different sub-tasks at this stage. Then, a compact radial basis function (RBF) network with fast learning speed and desirable generalization performance is applied as the sub-network to solve the corresponding task. On the one hand, the modular structure helps to improve the ability of neural networks on complex problems by implementing divide and conquer. On the other hand, sub-networks with considerable ability could guarantee the parsimonious and generalization of the entire neural network. Finally, the novel modular RBF (NM-RBF) network is evaluated through multiple benchmark numerical experiments, and results demonstrate that the NM-RBF network is capable of constructing a relative compact architecture during a short learning process with achievable satisfactory generalization performance, showing its effectiveness and outperformance.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-018-3763-z